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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "walk" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "walk" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    encies
    -0.84
    milo
    -0.80
    illian
    -0.78
    cffff
    -0.77
    afort
    -0.72
    anyahu
    -0.71
    nces
    -0.71
    ional
    -0.70
    nan
    -0.69
    iled
    -0.67
    POSITIVE LOGITS
    own
    0.98
    through
    0.97
    ways
    0.88
    about
    0.85
    Walk
    0.84
     Walk
    0.79
    bow
    0.78
    athon
    0.78
    ows
    0.78
    walk
    0.76
    Act Density 0.034%

    No Known Activations