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

    Neuronpedia

    INDEX
    Explanations

    information related to data analysis or investigation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the usefulness of data for decision-making and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shr
    -0.76
     Cursed
    -0.66
    yd
    -0.65
     fucked
    -0.63
     Nope
    -0.63
     screwed
    -0.62
     cel
    -0.61
     bailed
    -0.61
     disliked
    -0.60
     sacrificed
    -0.59
    POSITIVE LOGITS
     insights
    1.08
     decipher
    1.04
     insight
    1.02
     analyse
    0.94
     understanding
    0.91
     conclusions
    0.90
     enlight
    0.89
     dissemination
    0.89
     qualitative
    0.88
     analyze
    0.88
    Act Density 0.699%

    No Known Activations