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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 884
    Prev
    Next
    INDEX
    Explanations

    instances of characters expressing protest or objections

    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
    folios
    -0.69
    aurus
    -0.64
    ursed
    -0.63
    amiya
    -0.62
     hail
    -0.61
    secondary
    -0.60
    yx
    -0.60
    ubby
    -0.58
     specialized
    -0.57
    pez
    -0.57
    POSITIVE LOGITS
     bragging
    0.67
     meaning
    0.66
     enabling
    0.65
    ��
    0.64
     stating
    0.64
     informing
    0.64
    eny
    0.61
    tainment
    0.61
    meaning
    0.61
     explaining
    0.60
    Activations Density 0.386%

    No Known Activations