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

    Neuronpedia

    INDEX
    Explanations

    words related to entertainment or media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¨İ
    -0.15
    thinkable
    -0.15
    amen
    -0.14
    ierte
    -0.14
     vill
    -0.13
    uable
    -0.13
    isia
    -0.13
     kapas
    -0.13
     POR
    -0.13
     corrid
    -0.13
    POSITIVE LOGITS
    gel
    0.15
    ince
    0.15
    velt
    0.14
    ÑĢеб
    0.14
    ijd
    0.14
    FirstChild
    0.14
     Gel
    0.14
     vår
    0.14
    inez
    0.14
    obi
    0.14
    Act Density 0.000%

    No Known Activations