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

    Neuronpedia

    INDEX
    Explanations

    words related to exemptions or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exemptions and exceptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¥
    -0.77
    kr
    -0.70
     Xiang
    -0.69
     Zeit
    -0.65
     Roose
    -0.63
    plays
    -0.63
     Io
    -0.62
     Verge
    -0.62
     Toast
    -0.61
     Bras
    -0.61
    POSITIVE LOGITS
     exemptions
    1.13
     exempt
    1.03
     exemption
    1.03
     exempted
    0.93
     immunity
    0.92
    exempt
    0.87
    untarily
    0.80
    emption
    0.79
    icut
    0.78
     afforded
    0.77
    Act Density 0.033%

    No Known Activations