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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or thoughts of a male character

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "he" and its frequent occurrence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.70
     Header
    -0.67
     Mandatory
    -0.67
    regulation
    -0.61
    umption
    -0.60
     Leban
    -0.59
     Millennium
    -0.59
     Mile
    -0.59
    anking
    -0.58
     Gems
    -0.58
    POSITIVE LOGITS
    'd
    1.31
    resy
    1.25
    'll
    1.14
     himself
    1.13
    zbollah
    1.12
     thinks
    1.11
    ctic
    1.09
     knows
    1.09
    aped
    1.09
    eded
    1.09
    Act Density 0.375%

    No Known Activations