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

    Neuronpedia

    INDEX
    Explanations

    verbs related to explaining or categorizing

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    spot
    -0.73
    die
    -0.70
    ker
    -0.69
    guard
    -0.66
    onew
    -0.65
    corn
    -0.64
    Torrent
    -0.64
    bang
    -0.62
    win
    -0.61
    bott
    -0.60
    POSITIVE LOGITS
    ively
    1.12
    atively
    0.93
    urally
    0.91
     aspects
    0.90
    enance
    0.89
    ibly
    0.88
    ments
    0.87
    uate
    0.81
    ably
    0.80
     portions
    0.77
    Act Density 5.927%

    No Known Activations