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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "walk"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    encies
    -0.87
    nces
    -0.72
    iling
    -0.69
     circumstance
    -0.68
    afort
    -0.66
    iled
    -0.65
     pressures
    -0.65
     melt
    -0.64
    anyahu
    -0.64
    illian
    -0.64
    POSITIVE LOGITS
    through
    1.03
    about
    0.98
    own
    0.92
    ways
    0.92
     upright
    0.90
    bow
    0.89
    abouts
    0.87
    itzer
    0.84
    bows
    0.82
    way
    0.81
    Act Density 0.487%

    No Known Activations