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

    Neuronpedia

    INDEX
    Explanations

    numerical descriptions of quantities such as counts or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and specific time indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     swearing
    -0.68
     fluct
    -0.64
     swear
    -0.61
     fart
    -0.61
     "$:/
    -0.58
     toler
    -0.57
    Ĥİ
    -0.55
     conve
    -0.54
    theless
    -0.54
     distant
    -0.54
    POSITIVE LOGITS
    ½
    1.02
     ½
    1.00
    Pac
    0.94
    WD
    0.92
    UP
    0.88
    LT
    0.88
    GW
    0.84
    RM
    0.83
    200
    0.83
    DP
    0.83
    Act Density 0.111%

    No Known Activations