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

    Neuronpedia

    INDEX
    Explanations

    words related to participation and perspectives in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ursal
    -0.17
    igor
    -0.16
    ãĥªãĥ¼ãĤº
    -0.15
    engers
    -0.15
    PIO
    -0.15
    inox
    -0.15
    ahat
    -0.15
    readcr
    -0.15
    adients
    -0.15
    alars
    -0.15
    POSITIVE LOGITS
    412
    0.15
    543
    0.15
     Inquiry
    0.15
     inquiry
    0.14
    419
    0.14
     ph
    0.14
    flo
    0.14
    838
    0.14
    ands
    0.14
    897
    0.14
    Act Density 0.321%

    No Known Activations