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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sign, indication, or proof of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating signs or evidence of various conditions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tones
    -0.72
    onyms
    -0.72
    ancies
    -0.70
    ascus
    -0.67
    hari
    -0.66
     swaps
    -0.66
    quer
    -0.66
     Antiqu
    -0.65
    ulner
    -0.64
    asions
    -0.63
    POSITIVE LOGITS
    ariat
    0.72
    alled
    0.72
    ially
    0.72
     indication
    0.71
    ifier
    0.70
    Sign
    0.69
     indicative
    0.68
    rance
    0.67
     of
    0.67
    reader
    0.66
    Act Density 0.088%

    No Known Activations