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

    Neuronpedia

    INDEX
    Explanations

    phrases related to understanding and interpretation

    oai_token-act-pair · gpt-3.5-turbo

    references to understanding complex concepts or questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icides
    -0.84
    icide
    -0.75
    exclusive
    -0.74
    pload
    -0.71
    olphins
    -0.70
    veyard
    -0.70
    odder
    -0.69
    uable
    -0.69
    uxe
    -0.67
    icho
    -0.66
    POSITIVE LOGITS
     workings
    0.81
     Centauri
    0.73
     nuances
    0.73
     plight
    0.71
     limitations
    0.71
    ĨĴ
    0.69
     concepts
    0.68
     intric
    0.67
     lesson
    0.65
     Keynes
    0.65
    Act Density 0.192%

    No Known Activations