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

    Neuronpedia

    INDEX
    Explanations

    concepts related to moral philosophy and societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     frank
    -0.15
     ([[
    -0.15
    outs
    -0.14
    eca
    -0.14
    eka
    -0.14
    egade
    -0.14
    ionate
    -0.14
    Saga
    -0.14
    vier
    -0.13
    ker
    -0.13
    POSITIVE LOGITS
    rist
    0.16
     Carlson
    0.15
     cond
    0.14
     Minor
    0.14
    rahim
    0.13
     HAL
    0.13
     å§
    0.13
    _REGISTRY
    0.13
    entai
    0.13
    ãĤ¡
    0.13
    Act Density 0.003%

    No Known Activations