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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-identity and personal growth

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to self-identity and self-perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stopp
    -0.67
     rounds
    -0.65
     Bak
    -0.65
     popcorn
    -0.62
    warning
    -0.62
     OPEC
    -0.62
     pip
    -0.62
     buggy
    -0.61
     Stephenson
    -0.60
     Austrian
    -0.60
    POSITIVE LOGITS
    thood
    0.97
    hood
    0.95
     selves
    0.95
     persona
    0.91
    eness
    0.88
    selves
    0.88
     identity
    0.87
     esteem
    0.87
    conscious
    0.84
     pronouns
    0.83
    Act Density 0.179%

    No Known Activations