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

    Neuronpedia

    INDEX
    Explanations

    the word "whim" or similar words related to sudden desires or impulses

    oai_token-act-pair · gpt-3.5-turbo

    references to whims and spontaneous decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Detect
    -0.74
    ells
    -0.69
    Detect
    -0.66
     acknow
    -0.66
    Connection
    -0.63
    ociate
    -0.63
    ansen
    -0.63
    aucus
    -0.62
    archives
    -0.61
    nsic
    -0.61
    POSITIVE LOGITS
     whim
    3.91
     whims
    3.08
     behest
    1.18
     sway
    1.09
     rant
    1.03
     mercy
    1.01
     swoop
    0.99
     beck
    0.97
     pleading
    0.95
     vag
    0.93
    Act Density 0.041%

    No Known Activations