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

    Neuronpedia

    INDEX
    Explanations

    references to specific instances of time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "times" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ded
    -0.77
     pillow
    -0.70
    lished
    -0.68
    sie
    -0.67
    Assembly
    -0.64
    ding
    -0.64
    ntil
    -0.64
    isSpecialOrderable
    -0.64
    SpaceEngineers
    -0.62
     mattress
    -0.62
    POSITIVE LOGITS
    imes
    0.87
    hift
    0.84
    uate
    0.80
    cale
    0.75
    cript
    0.75
    pace
    0.73
    pec
    0.73
    ilver
    0.72
    sey
    0.70
    erve
    0.69
    Act Density 0.008%

    No Known Activations