© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2320
    Prev
    Next
    INDEX
    Explanations

    expressions of belief or conviction about personal or societal truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    went
    -0.82
    ��
    -0.77
    haven
    -0.71
    spection
    -0.69
    ギ
    -0.66
    borough
    -0.65
    _.
    -0.65
    :[
    -0.64
    VERSION
    -0.63
    mobi
    -0.63
    POSITIVE LOGITS
     important
    0.87
     taboo
    0.79
     apparent
    0.79
     acceptable
    0.77
     inevitable
    0.77
     problematic
    0.77
     crucial
    0.76
     essential
    0.75
     objectionable
    0.75
     advantageous
    0.74
    Activations Density 0.376%

    No Known Activations