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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their affiliations or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ead
    -0.17
    話
    -0.17
    getResult
    -0.15
    otos
    -0.15
    itos
    -0.14
    ordable
    -0.14
    apon
    -0.13
    öy
    -0.13
    AYS
    -0.13
    _probability
    -0.13
    POSITIVE LOGITS
    odia
    0.23
    wal
    0.23
    adoo
    0.19
    urve
    0.18
    oria
    0.18
    olia
    0.18
    deo
    0.17
    ãĥĨãĥ«
    0.17
     Dw
    0.16
    hani
    0.15
    Act Density 0.123%

    No Known Activations