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

    Neuronpedia

    INDEX
    Explanations

    phrases related to improving skills or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "up" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Anne
    -0.64
    oth
    -0.61
    mes
    -0.60
    ¯¯¯¯
    -0.60
    Closure
    -0.59
    ow
    -0.59
    Eye
    -0.58
    lean
    -0.58
    mouth
    -0.57
    BIT
    -0.57
    POSITIVE LOGITS
    river
    0.86
    hol
    0.80
    dates
    0.79
    raised
    0.77
     shop
    0.76
    grades
    0.74
    grading
    0.73
     nicely
    0.71
    dating
    0.68
    votes
    0.67
    Act Density 0.136%

    No Known Activations