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

    Neuronpedia

    INDEX
    Explanations

    words related to events or situations happening

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "occur" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilts
    -0.79
    acked
    -0.75
    education
    -0.73
    shaw
    -0.72
    rats
    -0.72
    step
    -0.72
    axter
    -0.70
    itzerland
    -0.69
    habi
    -0.69
    usting
    -0.69
    POSITIVE LOGITS
     occurring
    1.05
    rences
    0.95
     occurrences
    0.94
     occur
    0.92
    uate
    0.83
    Pause
    0.77
     occ
    0.77
    uated
    0.76
     occurrence
    0.75
     occurs
    0.73
    Act Density 0.013%

    No Known Activations