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

    Neuronpedia

    INDEX
    Explanations

    words related to accidental mistakes or errors

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "slip" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.67
    è¦ļéĨĴ
    -0.64
    inction
    -0.64
    nea
    -0.61
    rior
    -0.59
    ============
    -0.58
    uliffe
    -0.58
    ricular
    -0.57
    bell
    -0.57
    native
    -0.56
    POSITIVE LOGITS
     slip
    0.89
    stream
    0.83
    weed
    0.81
    bilt
    0.79
    opolis
    0.79
     slips
    0.77
    cover
    0.76
    ibrary
    0.76
     Whedon
    0.74
    uten
    0.74
    Act Density 0.009%

    No Known Activations