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

    Neuronpedia

    INDEX
    Explanations

    phrases related to spending money

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of producing or generating content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.77
     tyr
    -0.77
    cius
    -0.72
     Mub
    -0.63
     arsen
    -0.61
     examiner
    -0.60
     mathemat
    -0.57
     Citiz
    -0.57
     acqu
    -0.56
    amazon
    -0.56
    POSITIVE LOGITS
    wards
    1.05
    stretched
    0.99
    flows
    0.91
    fitted
    0.87
    flow
    0.83
    casts
    0.82
    doors
    0.76
    )=(
    0.75
    smart
    0.74
    grow
    0.72
    Act Density 0.065%

    No Known Activations