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

    Neuronpedia

    INDEX
    Explanations

    words indicating uncertainty or conjecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iya
    -0.86
    ortmund
    -0.73
    vers
    -0.73
    ieves
    -0.72
    ible
    -0.72
    issy
    -0.72
    Materials
    -0.71
    uctor
    -0.70
    etting
    -0.68
    icz
    -0.68
    POSITIVE LOGITS
     misunder
    0.80
     overest
    0.76
     underestimate
    0.75
     someday
    0.73
     gonna
    0.72
     underest
    0.72
     subconscious
    0.70
     exagger
    0.69
     somewhere
    0.69
     outwe
    0.68
    Act Density 0.024%

    No Known Activations