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

    Neuronpedia

    INDEX
    Explanations

    expressions of decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pais
    -0.65
    ypal
    -0.64
    FFFFFFFF
    -0.62
    িত
    -0.57
    crom
    -0.57
    bytes
    -0.57
     Oster
    -0.56
    issier
    -0.56
     berp
    -0.56
    oph
    -0.55
    POSITIVE LOGITS
     Decide
    1.67
     decides
    1.64
    Decide
    1.60
     Decided
    1.52
     decide
    1.51
     deciding
    1.46
    decide
    1.43
     decided
    1.43
    decided
    1.38
     décidé
    1.27
    Act Density 0.108%

    No Known Activations