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

    Neuronpedia

    INDEX
    Explanations

    words indicating a high degree of significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    the word "particularly" and related expressions emphasizing significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylon
    -0.71
    ences
    -0.68
    CT
    -0.65
    docs
    -0.65
    cli
    -0.63
    ORTS
    -0.63
    glers
    -0.63
    only
    -0.61
    cius
    -0.61
    TRY
    -0.61
    POSITIVE LOGITS
     egregious
    1.02
     suited
    1.01
     noteworthy
    0.95
     susceptible
    0.93
     noticeable
    0.88
     vulnerable
    0.86
     acute
    0.86
     advantageous
    0.85
     pronounced
    0.82
     fond
    0.81
    Act Density 0.039%

    No Known Activations