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

    Neuronpedia

    INDEX
    Explanations

    statements or declarations within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "statement" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rys
    -0.76
    MpServer
    -0.74
    bid
    -0.73
    elsius
    -0.71
    rowd
    -0.68
    Friend
    -0.68
    sites
    -0.67
    cffff
    -0.66
    rowing
    -0.66
    riot
    -0.64
    POSITIVE LOGITS
     statements
    0.90
    ariat
    0.84
     uttered
    0.82
    ARB
    0.80
     statement
    0.79
     regarding
    0.78
    gow
    0.78
     unequivocally
    0.76
     pronoun
    0.76
     aloud
    0.75
    Act Density 0.033%

    No Known Activations