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

    Neuronpedia

    INDEX
    Explanations

    contracted forms of "I am" or similar phrases containing "I'm"

    oai_token-act-pair · gpt-3.5-turbo

    the first-person pronoun "I" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subjects
    -0.67
     elite
    -0.63
     unaccompanied
    -0.60
     following
    -0.60
     unknown
    -0.59
     utility
    -0.59
     crowded
    -0.59
     tipping
    -0.57
     that
    -0.57
     those
    -0.57
    POSITIVE LOGITS
    'm
    2.94
     am
    1.58
    've
    1.54
    'll
    1.45
    're
    1.38
    'd
    1.29
    't
    1.02
     dunno
    0.96
     ain
    0.93
    Am
    0.92
    Act Density 0.019%

    No Known Activations