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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "signatures"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "signatures."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Afric
    -0.73
     Argon
    -0.69
    Hor
    -0.68
    »Ĵ
    -0.67
     nerv
    -0.63
     situational
    -0.62
     Virgin
    -0.62
     Adventures
    -0.62
    erest
    -0.61
     Continent
    -0.61
    POSITIVE LOGITS
     signatures
    1.05
     petitions
    1.00
    atories
    0.90
     petition
    0.90
    atures
    0.87
    ificant
    0.84
    wcsstore
    0.82
     captcha
    0.79
    ATURES
    0.77
    itional
    0.74
    Act Density 0.012%

    No Known Activations