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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal pronouns followed by a verb action

    oai_token-act-pair · gpt-3.5-turbo

    the word "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hips
    -0.68
     Dayton
    -0.68
     ears
    -0.67
     Polk
    -0.63
     pockets
    -0.61
    Priv
    -0.59
     footing
    -0.59
    feet
    -0.59
    lev
    -0.58
    ielding
    -0.58
    POSITIVE LOGITS
    alian
    1.06
    chy
    1.02
    iner
    0.97
    asca
    0.97
    ueller
    0.93
     seems
    0.92
     happened
    0.90
    zbollah
    0.89
    unes
    0.88
     transpired
    0.86
    Act Density 0.430%

    No Known Activations