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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating an event or action occurring

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "happen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ondo
    -0.88
    iple
    -0.79
    orney
    -0.76
    urdy
    -0.73
    rete
    -0.73
    imar
    -0.72
    ayers
    -0.71
    zie
    -0.71
    gebra
    -0.71
    aped
    -0.70
    POSITIVE LOGITS
     happen
    1.04
    rences
    0.89
     happening
    0.82
     occurrences
    0.81
     undone
    0.77
     occurring
    0.74
     Cthulhu
    0.73
     events
    0.72
     happened
    0.71
    Ñĭ
    0.71
    Act Density 0.016%

    No Known Activations