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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical regions or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uxe
    -0.93
     Skydragon
    -0.83
    isSpecialOrderable
    -0.80
     sanction
    -0.74
    onement
    -0.74
    wrong
    -0.68
     yawn
    -0.67
     suite
    -0.67
     deterrent
    -0.67
    rench
    -0.66
    POSITIVE LOGITS
    Posts
    0.91
    Assembly
    0.78
     Patient
    0.76
    Prin
    0.76
    regn
    0.76
    Reference
    0.75
    Const
    0.72
     ancest
    0.68
    Mech
    0.68
     Pig
    0.68
    Act Density 0.000%

    No Known Activations