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

    Neuronpedia

    INDEX
    Explanations

    phrases ending with commas and quotes

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating pauses or breaks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lance
    -0.68
    aware
    -0.67
    FIN
    -0.67
    lik
    -0.66
     appra
    -0.64
    escription
    -0.63
    knit
    -0.62
    haus
    -0.62
    eg
    -0.61
    past
    -0.61
    POSITIVE LOGITS
    neau
    0.75
     Flavoring
    0.74
     CCP
    0.70
    netflix
    0.69
     Died
    0.68
    xual
    0.67
    Leary
    0.66
     HSBC
    0.66
     Walters
    0.66
    vasive
    0.65
    Act Density 0.000%

    No Known Activations