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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals and research citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     putas
    -0.16
    landing
    -0.15
    adolu
    -0.15
     Äiju
    -0.15
    rido
    -0.14
    roys
    -0.14
    adu
    -0.14
    ustil
    -0.14
    uÄį
    -0.14
    uÅŁ
    -0.14
    POSITIVE LOGITS
    atura
    0.16
    VAS
    0.15
    iali
    0.15
     bra
    0.15
    sam
    0.15
    crop
    0.14
     faç
    0.13
    Ñıв
    0.13
    320
    0.13
     Evil
    0.13
    Act Density 0.229%

    No Known Activations