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

    Neuronpedia

    INDEX
    Explanations

    positive emotions or expressions of satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positive emotions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helicop
    -0.86
    arettes
    -0.72
     contaminated
    -0.68
     controlled
    -0.67
     trailed
    -0.64
    plane
    -0.63
    flat
    -0.61
     sneak
    -0.60
     indo
    -0.59
    outed
    -0.59
    POSITIVE LOGITS
    joy
    0.75
     Parish
    0.72
    dy
    0.68
     âĶľ
    0.68
    Ĥª
    0.67
     congratulations
    0.65
    DAQ
    0.64
     fortunate
    0.63
    quartered
    0.62
    inite
    0.62
    Act Density 0.054%

    No Known Activations