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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating upper limits or maximum values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esses
    -0.18
    ury
    -0.17
    ulumi
    -0.15
    nt
    -0.15
    zw
    -0.15
    ãĥ¼ãĥĭ
    -0.14
    ne
    -0.14
     Spears
    -0.14
    our
    -0.14
    åĩ¡
    -0.14
    POSITIVE LOGITS
    /down
    0.24
    azzo
    0.18
    alli
    0.15
    ToDate
    0.15
    rias
    0.15
    iyon
    0.14
    opa
    0.14
    ipes
    0.14
    verture
    0.14
    .Toolkit
    0.14
    Act Density 0.026%

    No Known Activations