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

    Neuronpedia

    INDEX
    Explanations

    colons and their associated statements or labels in titles and headings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arest
    -0.16
    apt
    -0.15
    RYPT
    -0.15
    bage
    -0.14
    ided
    -0.14
    BJECT
    -0.14
    CriticalSection
    -0.14
    ÅĤaw
    -0.14
    Å¡i
    -0.14
    ATALOG
    -0.13
    POSITIVE LOGITS
    eyse
    0.16
    -widgets
    0.15
     Silent
    0.14
    eyh
    0.13
    /card
    0.13
     TAS
    0.13
     Ches
    0.13
     ‘
    0.13
    Inputs
    0.13
     Silva
    0.13
    Act Density 0.030%

    No Known Activations