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

    Neuronpedia

    INDEX
    Explanations

    mentions of computing or technology, especially related to bots or digital threats

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    mble
    -0.80
    mund
    -0.73
     pact
    -0.65
     McCartney
    -0.62
    ity
    -0.62
    vid
    -0.62
    egal
    -0.61
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.61
    VEN
    -0.60
    ities
    -0.60
    POSITIVE LOGITS
    anical
    1.33
    anie
    1.02
    wana
    1.01
    anooga
    0.97
    cham
    0.97
    zeb
    0.94
    anic
    0.94
    ania
    0.94
    any
    0.90
    herer
    0.89
    Act Density 0.198%

    No Known Activations