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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 325
    Prev
    Next
    INDEX
    Explanations

    terms indicating negative judgments or opinions about something being nonsensical or foolish

    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
     Included
    -0.76
    �
    -0.75
    avia
    -0.68
    agara
    -0.66
    ambers
    -0.66
    essen
    -0.66
    hua
    -0.65
    aught
    -0.65
    ema
    -0.65
    psey
    -0.64
    POSITIVE LOGITS
    Thom
    0.70
     VICE
    0.67
     DMCA
    0.67
    itude
    0.65
    }}}
    0.64
    pmwiki
    0.64
    Torrent
    0.63
    "}
    0.62
    oit
    0.60
     breeze
    0.60
    Activations Density 0.191%

    No Known Activations