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

    Neuronpedia

    INDEX
    Explanations

    References to time-based phrases or temporal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éłĨ
    -0.15
    tabs
    -0.14
    Genres
    -0.14
    geb
    -0.13
    pee
    -0.13
    edd
    -0.13
     عبار
    -0.13
    '",
    -0.13
    ãĥ¨
    -0.13
     Dana
    -0.13
    POSITIVE LOGITS
     twice
    0.16
    odus
    0.15
    nad
    0.15
    iad
    0.14
    itaire
    0.14
    ãĥ¼ãĥŀ
    0.14
    uth
    0.13
    alion
    0.13
     Fon
    0.13
    nist
    0.13
    Act Density 0.852%

    No Known Activations