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

    Neuronpedia

    INDEX
    Explanations

    financial figures in various currencies

    oai_token-act-pair · gpt-3.5-turbo

    parentheses in numerical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itory
    -0.73
     artif
    -0.69
     answ
    -0.68
     administrator
    -0.67
    ahu
    -0.65
    Ń·
    -0.65
    ounding
    -0.64
    ĵĺ
    -0.61
    omorphic
    -0.60
    resa
    -0.58
    POSITIVE LOGITS
    ãĥİ
    0.70
     Gamb
    0.70
    ²
    0.64
    âĢ¦)
    0.62
     Frames
    0.61
    yards
    0.61
     Unloaded
    0.60
    >]
    0.60
    eous
    0.60
    *.
    0.60
    Act Density 0.106%

    No Known Activations