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

    Neuronpedia

    INDEX
    Explanations

    the modal verb "may" followed by various numerical values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "may" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fighter
    -0.71
    ging
    -0.67
     Bagg
    -0.63
     Enforcement
    -0.63
     Dragonbound
    -0.62
    icial
    -0.62
    feeding
    -0.62
     Constant
    -0.61
    raphic
    -0.60
     Programme
    -0.60
    POSITIVE LOGITS
    hap
    1.11
    onna
    0.95
    haps
    0.92
    bes
    0.90
    nard
    0.84
     misunder
    0.75
     someday
    0.74
    weather
    0.74
     feas
    0.73
    afort
    0.71
    Act Density 0.073%

    No Known Activations