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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "he" followed by an action or description

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "he" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    requisite
    -0.71
    etheless
    -0.69
    veyard
    -0.67
     Gems
    -0.65
     Leban
    -0.62
    mary
    -0.60
    services
    -0.60
    iries
    -0.60
    Interest
    -0.59
     Claire
    -0.58
    POSITIVE LOGITS
    'd
    1.08
    resy
    1.07
    'll
    1.07
    eded
    1.04
    uristic
    1.03
    zbollah
    1.03
     Majesty
    0.92
    ctic
    0.89
    eding
    0.89
    aps
    0.89
    Act Density 0.344%

    No Known Activations