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

    Neuronpedia

    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -0.63
     finances
    -0.62
     coales
    -0.62
     neglig
    -0.61
     oun
    -0.61
     neighb
    -0.60
     vanity
    -0.58
     challeng
    -0.57
     spr
    -0.57
     conqu
    -0.56
    POSITIVE LOGITS
    m
    1.39
    ms
    1.04
    mk
    1.04
    pm
    1.02
    mx
    0.98
    mt
    0.98
    fm
    0.97
    meter
    0.97
    mid
    0.96
    dm
    0.96
    Act Density 0.018%

    No Known Activations