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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or actions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and its frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    caster
    -0.77
    League
    -0.72
    itionally
    -0.72
    apest
    -0.70
    uously
    -0.69
    oun
    -0.69
    olate
    -0.68
    pton
    -0.66
    tains
    -0.66
    vre
    -0.65
    POSITIVE LOGITS
     coli
    0.66
     lest
    0.66
    stretched
    0.66
     Expend
    0.62
     Faster
    0.61
     Collider
    0.61
    repeat
    0.61
     DISTRICT
    0.60
     Orders
    0.60
     Plane
    0.59
    Act Density 0.601%

    No Known Activations