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

    Neuronpedia

    INDEX
    Explanations

    personal statements where the speaker expresses their thoughts or feelings about something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of self-identity and the speaker's personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kut
    -0.70
    boards
    -0.67
    iquette
    -0.66
     Rolls
    -0.62
     Razor
    -0.62
    theless
    -0.61
    Snake
    -0.60
    birds
    -0.60
     Shel
    -0.59
    bones
    -0.58
    POSITIVE LOGITS
     am
    3.38
     Am
    1.74
    Am
    1.67
     pm
    1.59
     AM
    1.57
    'm
    1.56
    am
    1.39
    AM
    1.19
    amic
    0.98
     im
    0.95
    Act Density 0.033%

    No Known Activations