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

    Neuronpedia

    INDEX
    Explanations

    specific times indicated in a text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "at" as a preposition indicating time or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reditary
    -0.65
    isphere
    -0.63
    FTWARE
    -0.63
    plane
    -0.62
    chuk
    -0.61
    Tube
    -0.59
    biased
    -0.59
     prescriptions
    -0.58
     thereof
    -0.56
    selves
    -0.55
    POSITIVE LOGITS
     least
    1.04
    mosp
    1.04
    yp
    0.93
    onement
    0.90
    las
    0.88
    mega
    0.82
    hens
    0.81
    raz
    0.81
    acan
    0.78
    ention
    0.77
    Act Density 0.036%

    No Known Activations