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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs indicating the occurrence of an event

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "happened" to denote events or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilts
    -0.79
    edged
    -0.79
    ench
    -0.78
    oug
    -0.76
    grown
    -0.75
    ogo
    -0.74
    uffed
    -0.74
    arta
    -0.73
    urdy
    -0.73
    tan
    -0.72
    POSITIVE LOGITS
     happening
    0.77
    cffffcc
    0.77
     occ
    0.72
     Procedure
    0.71
     Ambro
    0.71
     Weinstein
    0.70
     unfolding
    0.68
     psychiat
    0.67
     occurring
    0.67
    Eva
    0.67
    Act Density 0.040%

    No Known Activations