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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications and mathematical literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bunker
    -0.17
    _simps
    -0.16
    ÃŃl
    -0.15
    гÑĥ
    -0.14
     Arthur
    -0.14
     luc
    -0.14
    ucha
    -0.14
    oren
    -0.14
    RK
    -0.14
     bypass
    -0.14
    POSITIVE LOGITS
     Dank
    0.16
     Elect
    0.15
    izz
    0.15
    esModule
    0.15
     datatype
    0.14
    elect
    0.14
    762
    0.14
     Preconditions
    0.14
    ataka
    0.14
    ogg
    0.14
    Act Density 0.347%

    No Known Activations