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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĢ
    -0.16
    udev
    -0.15
    pll
    -0.14
    prs
    -0.14
    fx
    -0.14
    ato
    -0.14
    cq
    -0.14
    bon
    -0.14
    bare
    -0.14
    gado
    -0.14
    POSITIVE LOGITS
    ìŀIJ기
    0.14
    .criteria
    0.14
    ORTH
    0.14
    licing
    0.14
    anst
    0.14
    .Criteria
    0.14
    ãģĹãģ®
    0.14
    oting
    0.13
    ξι
    0.13
    edo
    0.13
    Act Density 0.014%

    No Known Activations