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

    Neuronpedia

    INDEX
    Explanations

    words related to fitting, compatibility, or alignment

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to conformity or compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cember
    -0.68
    bies
    -0.66
    wcs
    -0.62
    affer
    -0.61
    externalActionCode
    -0.61
     descend
    -0.61
    icide
    -0.59
    escal
    -0.59
    icious
    -0.59
     salute
    -0.58
    POSITIVE LOGITS
     snug
    1.15
    gerald
    0.97
     into
    0.95
    ¶æ
    0.80
    nah
    0.77
    kat
    0.77
     squarely
    0.76
     comfortably
    0.74
     onto
    0.72
     neatly
    0.70
    Act Density 0.045%

    No Known Activations