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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "I."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "I"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cost
    -0.65
     Edison
    -0.63
     Uriel
    -0.61
     Clancy
    -0.61
     Hazard
    -0.60
     mutants
    -0.60
     McKin
    -0.59
     tides
    -0.59
     Alternative
    -0.58
    wikipedia
    -0.58
    POSITIVE LOGITS
    'm
    1.50
    've
    1.31
     suppose
    1.13
    'd
    1.08
     am
    1.03
    ggy
    1.02
     presume
    0.99
    RL
    0.98
    'll
    0.96
     guess
    0.92
    Act Density 0.211%

    No Known Activations