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

    Neuronpedia

    INDEX
    Explanations

    concepts of accountability, morality, and the rightness of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ineligible
    -0.17
    rypton
    -0.15
    ÄĻż
    -0.15
    izu
    -0.14
    znik
    -0.14
     unforgettable
    -0.13
     Keyword
    -0.13
     Nicholson
    -0.13
     Availability
    -0.13
    ainter
    -0.13
    POSITIVE LOGITS
     exped
    0.28
     wise
    0.27
     appropriate
    0.26
     smart
    0.25
     logical
    0.24
     consc
    0.24
     rational
    0.24
     sound
    0.24
     proper
    0.24
     justified
    0.23
    Act Density 0.314%

    No Known Activations