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

    Neuronpedia

    INDEX
    Explanations

    numbers or numeric references that have been mentioned in a textual context

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "so far" indicating progress or cumulative events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ysis
    -0.70
    degree
    -0.60
    ounce
    -0.59
    ANT
    -0.58
    responsible
    -0.57
     moder
    -0.56
    exclusive
    -0.56
    unts
    -0.54
    thro
    -0.54
     Franç
    -0.54
    POSITIVE LOGITS
     far
    1.78
    far
    1.57
     FAR
    1.16
    Far
    1.07
     Far
    1.01
    ared
    0.95
    bered
    0.95
    aring
    0.93
    arer
    0.92
    othes
    0.89
    Act Density 0.059%

    No Known Activations