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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing certainty or strong evidence

    oai_token-act-pair · gpt-3.5-turbo

    words indicating certainty or undeniable facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isson
    -0.81
     Hunting
    -0.80
     Higgins
    -0.74
     Cullen
    -0.73
     Loft
    -0.73
    ÃŁ
    -0.70
    onz
    -0.69
     Rounds
    -0.67
     Grants
    -0.67
    eries
    -0.67
    POSITIVE LOGITS
     unmist
    1.04
     conclusive
    0.93
     indis
    0.91
     unamb
    0.90
    putable
    0.88
    akable
    0.86
     unequiv
    0.77
     unequivocally
    0.76
     definitively
    0.76
    charged
    0.76
    Act Density 0.011%

    No Known Activations