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

    Neuronpedia

    INDEX
    Explanations

    excitement or enthusiasm in statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iciency
    -0.72
     dated
    -0.71
    avis
    -0.70
    mine
    -0.68
     smuggled
    -0.67
     flaw
    -0.63
    outs
    -0.63
    abases
    -0.62
     outlawed
    -0.62
    arin
    -0.62
    POSITIVE LOGITS
    GGGGGGGG
    0.86
     anticipation
    0.81
    ly
    0.77
    GGGG
    0.77
    NESS
    0.74
    ctl
    0.71
    iously
    0.69
     excited
    0.68
    vier
    0.68
    ÃįÃį
    0.67
    Act Density 0.035%

    No Known Activations