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

    Neuronpedia

    INDEX
    Explanations

    phrases that express the state or condition of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubl
    -0.16
    YK
    -0.15
    nop
    -0.15
    231
    -0.14
    stable
    -0.14
    iddet
    -0.14
    ÑĪÑĤов
    -0.14
     Goldberg
    -0.14
    meg
    -0.14
    ottle
    -0.14
    POSITIVE LOGITS
    -prefix
    0.14
    во
    0.14
    inger
    0.14
    .overflow
    0.14
    buah
    0.14
    asse
    0.14
    antro
    0.14
    haar
    0.13
    æĪIJ
    0.13
    .mask
    0.13
    Act Density 0.178%

    No Known Activations