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

    Neuronpedia

    INDEX
    Explanations

    references to guidelines and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.19
     Henri
    -0.16
    é¦Ļ
    -0.15
    ovy
    -0.14
     Main
    -0.14
    ader
    -0.14
     O
    -0.13
    bound
    -0.13
     Gst
    -0.13
    ret
    -0.13
    POSITIVE LOGITS
    rone
    0.15
    Ñħов
    0.14
    άÏĤ
    0.14
    γά
    0.14
    soever
    0.14
    sd
    0.14
    ridor
    0.14
    ificador
    0.14
    usz
    0.14
    ishop
    0.14
    Act Density 0.003%

    No Known Activations