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

    Neuronpedia

    INDEX
    Explanations

    generic action verbs related to exploration and discovery

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "explore" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivari
    -0.71
    fight
    -0.69
    jud
    -0.69
    fixed
    -0.65
    iah
    -0.63
    gage
    -0.62
    lat
    -0.61
    wa
    -0.60
    processing
    -0.60
    cake
    -0.59
    POSITIVE LOGITS
    ationally
    0.91
    vier
    0.86
     avenues
    0.82
    ibilities
    0.81
    nels
    0.80
    schild
    0.79
    prising
    0.78
    Ô
    0.78
    çīĪ
    0.78
    ĸļ
    0.78
    Act Density 0.033%

    No Known Activations