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

    Neuronpedia

    INDEX
    Explanations

    references to male characters and pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ssz
    -0.61
    setShow
    -0.60
     inva
    -0.59
     aig
    -0.59
     similar
    -0.56
     Noch
    -0.56
     comod
    -0.54
     fora
    -0.53
    ancia
    -0.53
     dima
    -0.53
    POSITIVE LOGITS
     himself
    1.42
     he
    1.35
    himself
    1.30
    He
    1.24
     she
    1.22
     He
    1.22
    tvguidetime
    1.20
     Himself
    1.17
    OGND
    1.15
    she
    1.14
    Act Density 0.285%

    No Known Activations