© 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. 825
    Prev
    Next
    INDEX
    Explanations

    mentions of petitions

    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
    aspers
    -0.86
    llah
    -0.70
    ntil
    -0.70
     tremend
    -0.67
    reditary
    -0.67
    uably
    -0.65
    =-=-=-=-
    -0.63
    dfx
    -0.62
    @#&
    -0.60
    ngth
    -0.60
    POSITIVE LOGITS
    覚醒
    0.69
    hill
    0.66
    adding
    0.62
    DEBUG
    0.61
    Whit
    0.61
    ranged
    0.59
    skirts
    0.58
    Process
    0.58
    Smith
    0.57
    Cook
    0.57
    Activations Density 0.035%

    No Known Activations