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

    Neuronpedia

    INDEX
    Explanations

    rankings and comparative statistics regarding performance or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stoff
    -0.15
    anke
    -0.15
    anh
    -0.13
    ContextHolder
    -0.13
    utes
    -0.13
    _PRINTF
    -0.13
    /maps
    -0.13
     Ivory
    -0.13
     Dependencies
    -0.13
    han
    -0.13
    POSITIVE LOGITS
    ENTA
    0.17
    oland
    0.16
    aska
    0.16
    &action
    0.14
    391
    0.14
     رÙĤÙħ
    0.14
    رز
    0.14
    585
    0.13
    utow
    0.13
     dash
    0.13
    Act Density 0.042%

    No Known Activations