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

    Neuronpedia

    INDEX
    Explanations

    phrases related to multiple instances or quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.72
    ĸļ
    -0.72
    acus
    -0.71
    usp
    -0.68
    hesis
    -0.68
    ared
    -0.67
    aceous
    -0.67
    acle
    -0.65
    ifier
    -0.63
    vest
    -0.63
    POSITIVE LOGITS
     unanswered
    0.95
     occasions
    0.90
     iterations
    0.84
     times
    0.84
     factors
    0.83
     instances
    0.81
     articles
    0.80
     ailments
    0.79
     episodes
    0.77
     ways
    0.76
    Act Density 0.087%

    No Known Activations