Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 173
    Prev
    Next
    INDEX
    Explanations

    references to significant changes or impacts on people's perspectives and realities

    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
    oen
    -0.95
    cules
    -0.82
    owship
    -0.80
    mania
    -0.80
    版
    -0.78
    ousands
    -0.77
    acha
    -0.77
    ESE
    -0.75
    ��
    -0.74
    RANT
    -0.72
    POSITIVE LOGITS
     nature
    0.84
    indal
    0.82
     rhythm
    0.81
     fundament
    0.76
     fact
    0.75
     phr
    0.74
     trajectory
    0.73
     way
    0.73
     belie
    0.73
     ante
    0.72
    Activations Density 0.082%

    No Known Activations