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

    Neuronpedia

    INDEX
    Explanations

    technical terms and specific programming or data-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seg
    -0.16
    pare
    -0.16
    bak
    -0.15
    amac
    -0.15
    ker
    -0.14
     bÃło
    -0.14
    adin
    -0.14
    ÃŃg
    -0.14
    ewing
    -0.14
    =Value
    -0.14
    POSITIVE LOGITS
     Neutral
    0.17
    Neutral
    0.17
     neutral
    0.15
    yaw
    0.15
     neutrality
    0.15
    uzey
    0.15
    asz
    0.15
     Woodward
    0.14
    ãĥĨãĥ«
    0.14
    ÑĥÑĢи
    0.14
    Act Density 0.042%

    No Known Activations