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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and code snippets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     cutting
    -0.74
     tink
    -0.69
     MEN
    -0.63
     pound
    -0.63
     Gallup
    -0.62
     ounce
    -0.62
     WATCHED
    -0.61
     Samar
    -0.61
     scream
    -0.60
     Methodist
    -0.60
    POSITIVE LOGITS
    alist
    1.24
    container
    1.11
    edition
    1.07
    wrapper
    1.02
    det
    1.00
    type
    1.00
    controller
    0.99
    style
    0.99
    mode
    0.98
    distance
    0.97
    Act Density 0.080%

    No Known Activations