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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and related verbs

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and phrases expressing personal opinions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imum
    -0.80
    é¾įå¥ij士
    -0.75
    ðĿ
    -0.74
    quartered
    -0.73
    unknown
    -0.71
    unin
    -0.71
    assembly
    -0.71
    -+-+
    -0.70
    tnc
    -0.68
    phans
    -0.68
    POSITIVE LOGITS
     lied
    0.76
     exagger
    0.75
     mention
    0.74
     kidding
    0.73
     forgot
    0.72
     exaggeration
    0.70
     typo
    0.68
     guessed
    0.68
     cheated
    0.68
     cried
    0.67
    Act Density 0.153%

    No Known Activations