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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a specific occurrence or event

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "happen" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilts
    -0.90
    ware
    -0.85
    edged
    -0.80
    ament
    -0.74
    hetic
    -0.74
    ordes
    -0.72
    waukee
    -0.72
    heddar
    -0.72
    amental
    -0.70
    igration
    -0.70
    POSITIVE LOGITS
    rences
    0.80
    uate
    0.78
    uates
    0.77
     Tues
    0.70
     Ambro
    0.69
     unavoid
    0.67
     naturally
    0.66
     Pall
    0.65
     disturb
    0.64
    Ń·
    0.64
    Act Density 0.032%

    No Known Activations