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

    Neuronpedia

    INDEX
    Explanations

    verbs expressing disagreement or challenge

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    SizeMode
    -0.59
     Unies
    -0.53
     quibus
    -0.50
    zene
    -0.49
     Picchu
    -0.48
    lgica
    -0.48
     fosfor
    -0.48
    NRAS
    -0.47
    MLLoader
    -0.47
     etik
    -0.46
    POSITIVE LOGITS
     shenan
    1.20
     disreg
    1.12
     unspeak
    1.00
     maneu
    0.97
     suscep
    0.93
     reluct
    0.91
     intersper
    0.91
     apprehen
    0.90
     horrend
    0.86
     sophistic
    0.85
    Act Density 0.288%

    No Known Activations