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

    Neuronpedia

    INDEX
    Explanations

    adverbs that emphasize speed or swiftness

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating realization or awareness of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alli
    -0.61
    isec
    -0.61
     mathemat
    -0.58
    Pg
    -0.57
     ensu
    -0.57
     cov
    -0.56
     equals
    -0.56
    uper
    -0.54
    eteria
    -0.54
     showc
    -0.54
    POSITIVE LOGITS
    that
    0.97
     how
    0.91
     why
    0.87
    whether
    0.84
     whether
    0.83
    how
    0.80
     that
    0.79
    why
    0.78
    what
    0.76
    fficiency
    0.71
    Act Density 0.288%

    No Known Activations