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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names such as "Clayton", "Allison", and "Jarrett"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly the name "Clayton" and variances of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lda
    -0.93
    asus
    -0.90
    ername
    -0.88
    meric
    -0.87
    ounded
    -0.86
    ÅŁ
    -0.85
    mented
    -0.84
    ublic
    -0.79
    rament
    -0.79
    lesi
    -0.78
    POSITIVE LOGITS
     judgment
    0.79
     judgement
    0.76
    ovie
    0.72
     equilibrium
    0.71
     judgments
    0.68
     glances
    0.67
     suites
    0.66
     skies
    0.65
    anguage
    0.62
     bursts
    0.62
    Act Density 0.041%

    No Known Activations