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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes over time and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Library
    -0.15
    asar
    -0.14
    ufe
    -0.14
    @protocol
    -0.14
    OUCH
    -0.14
    erule
    -0.14
    æ´
    -0.14
    DialogContent
    -0.14
    indow
    -0.13
     Shape
    -0.13
    POSITIVE LOGITS
    694
    0.17
    fect
    0.17
     Sher
    0.16
    ropoda
    0.15
    732
    0.15
    484
    0.15
    580
    0.15
    641
    0.15
    624
    0.14
    947
    0.14
    Act Density 0.265%

    No Known Activations