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

    Neuronpedia

    INDEX
    Explanations

    the pronoun 'I'

    oai_token-act-pair · gpt-3.5-turbo

    pronouns that express personal sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Uriel
    -0.63
     Sidney
    -0.58
     mutants
    -0.58
     Nora
    -0.58
     Gale
    -0.57
    illary
    -0.57
    cedes
    -0.56
    eworthy
    -0.55
     Alternative
    -0.55
     Violet
    -0.55
    POSITIVE LOGITS
    'm
    1.57
    've
    1.29
     am
    1.18
     suppose
    1.05
    RL
    1.04
    'd
    1.02
     myself
    0.97
    'll
    0.94
     presume
    0.94
    ggy
    0.91
    Act Density 0.219%

    No Known Activations