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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to activities or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    patterns of responsibility and accountability in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogether
    -0.68
    selves
    -0.64
    emale
    -0.63
    common
    -0.62
     discrep
    -0.60
     respectively
    -0.60
    aminer
    -0.57
    joice
    -0.57
    earch
    -0.56
     Composite
    -0.56
    POSITIVE LOGITS
     himself
    0.95
     Himself
    0.66
     remorse
    0.61
     resign
    0.59
     personally
    0.57
     solo
    0.55
     his
    0.54
     apolog
    0.54
    zbollah
    0.53
     beard
    0.52
    Act Density 0.753%

    No Known Activations