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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "impossible."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ark
    -0.16
    enz
    -0.15
    umor
    -0.15
    alth
    -0.14
     cris
    -0.14
    uning
    -0.14
     Reader
    -0.14
    AMP
    -0.14
    adan
    -0.14
    OA
    -0.14
    POSITIVE LOGITS
     anybody
    0.16
    ubat
    0.15
    ffe
    0.15
     Gree
    0.15
    365
    0.15
    ccoli
    0.15
    åĩ¡
    0.15
    sterol
    0.14
    mann
    0.14
    pedia
    0.14
    Act Density 0.010%

    No Known Activations