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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions denoting a countdown or interval before a future event

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities that are less than a certain amount

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³
    -0.67
    tera
    -0.67
    vl
    -0.64
    File
    -0.63
    ç«
    -0.63
    illary
    -0.61
    LOS
    -0.61
     ALSO
    -0.61
    IED
    -0.60
    find
    -0.60
    POSITIVE LOGITS
     half
    1.07
     halfway
    1.02
     stellar
    0.99
    stellar
    0.87
    icable
    0.87
    whelming
    0.84
     satisfactory
    0.84
     ½
    0.81
     flattering
    0.80
     ideal
    0.78
    Act Density 0.052%

    No Known Activations