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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns referencing 'he'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "he."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earch
    -0.70
    anking
    -0.69
    requisite
    -0.67
    htaking
    -0.67
    veyard
    -0.66
    iries
    -0.65
     Mandatory
    -0.65
    iscovery
    -0.64
    uy
    -0.64
    regulation
    -0.63
    POSITIVE LOGITS
    'd
    1.24
    eded
    1.06
    'll
    1.05
    resy
    0.96
     knew
    0.93
    zbollah
    0.92
     thinks
    0.88
    aped
    0.87
    ctic
    0.87
    uristic
    0.87
    Act Density 0.351%

    No Known Activations