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

    Neuronpedia

    INDEX
    Explanations

    phrases describing specific incidents or accidents

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to incidents or events, particularly those involving accidents or crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scholarship
    -0.61
    ertain
    -0.60
    Marginal
    -0.59
    IE
    -0.59
    coat
    -0.58
    ĪĴ
    -0.57
    nor
    -0.57
    bro
    -0.56
    ngth
    -0.55
     Creator
    -0.53
    POSITIVE LOGITS
     shortly
    1.12
     AFTER
    1.02
     hours
    1.00
     midday
    0.99
     while
    0.98
     sometime
    0.98
     amid
    0.95
     during
    0.95
     Wednesday
    0.92
     Tuesday
    0.92
    Act Density 0.169%

    No Known Activations