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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and excitement related to support and achievements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prefers
    -0.65
     favoring
    -0.62
    ware
    -0.62
     beware
    -0.62
     respectively
    -0.61
     Bent
    -0.58
    ibaba
    -0.57
     Preferred
    -0.56
    ussed
    -0.56
     blamed
    -0.55
    POSITIVE LOGITS
    !]
    0.89
    querade
    0.69
    agos
    0.68
     ASA
    0.64
    !!!!!!!!
    0.61
    imity
    0.60
    rats
    0.59
     opportunity
    0.59
    ],"
    0.58
    ouncing
    0.58
    Act Density 0.530%

    No Known Activations