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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to losing control or letting something unintended happen

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "slip" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.69
    inction
    -0.67
    types
    -0.63
    nea
    -0.62
    ``
    -0.61
    resident
    -0.61
    da
    -0.60
    è¦ļéĨĴ
    -0.60
    ============
    -0.59
    eals
    -0.58
    POSITIVE LOGITS
     slip
    0.91
    bilt
    0.88
    weed
    0.81
     slips
    0.78
     Whedon
    0.75
    avier
    0.74
    opolis
    0.73
    crew
    0.73
    uten
    0.69
    adoes
    0.69
    Act Density 0.007%

    No Known Activations