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

    Neuronpedia

    INDEX
    Explanations

    positively evaluated actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sound decision-making or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oreal
    -0.72
    ļéĨĴ
    -0.70
    anguage
    -0.68
    stories
    -0.68
    icone
    -0.68
    aura
    -0.68
    resy
    -0.67
    ench
    -0.66
    ampions
    -0.66
    ringe
    -0.65
    POSITIVE LOGITS
     decisions
    1.11
     decision
    1.10
     timing
    1.09
     execution
    1.05
     prudent
    1.04
     manoeuv
    0.99
     omission
    0.99
     deliberate
    0.96
     choices
    0.94
     executed
    0.92
    Act Density 0.687%

    No Known Activations