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

    Neuronpedia

    INDEX
    Explanations

    expressions of choice or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uality
    -0.21
    zzo
    -0.15
    da
    -0.15
    typeid
    -0.15
    toy
    -0.15
    atcher
    -0.15
    uling
    -0.15
    logue
    -0.15
    lico
    -0.14
    licht
    -0.14
    POSITIVE LOGITS
     wisely
    0.27
    entially
    0.25
     Wis
    0.23
     lá»įc
    0.23
     between
    0.21
     sides
    0.19
     among
    0.18
    ItemAt
    0.18
    wis
    0.17
    'gc
    0.17
    Act Density 0.030%

    No Known Activations