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

    Neuronpedia

    INDEX
    Explanations

    calendars or references to locations with the word "cal" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "cal" and variations of "Sul."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blackburn
    -0.77
    III
    -0.75
    eers
    -0.75
     Hook
    -0.72
    ealous
    -0.71
    ttes
    -0.71
     Sins
    -0.70
     Faust
    -0.68
     Sons
    -0.68
     Lesbian
    -0.68
    POSITIVE LOGITS
     cal
    1.31
    qus
    0.90
    pered
    0.85
     gobl
    0.83
    otrop
    0.79
    EStreamFrame
    0.78
    ipers
    0.78
    pher
    0.77
    ignty
    0.77
    culus
    0.76
    Act Density 0.016%

    No Known Activations