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

    Neuronpedia

    INDEX
    Explanations

    references to stories or articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ائ
    -0.16
     Fus
    -0.14
    sworth
    -0.14
    thon
    -0.14
     excess
    -0.14
    erb
    -0.13
     Everest
    -0.13
    er
    -0.13
     Feather
    -0.13
    y
    -0.13
    POSITIVE LOGITS
    ulas
    0.17
    umer
    0.16
    PLE
    0.15
    adan
    0.14
    plied
    0.14
     åº
    0.14
    aight
    0.14
    ulp
    0.14
    .RELATED
    0.14
    pta
    0.14
    Act Density 0.012%

    No Known Activations