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

    Neuronpedia

    INDEX
    Explanations

    exceptions to rules or norms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    DCS
    -0.70
     destro
    -0.68
    MT
    -0.67
    ching
    -0.66
     misinformation
    -0.59
    Progress
    -0.59
     opio
    -0.59
     pestic
    -0.59
    ched
    -0.59
    Cho
    -0.58
    POSITIVE LOGITS
    ĸļ
    0.98
    ional
    0.91
    arily
    0.84
    als
    0.84
    abl
    0.80
     exception
    0.78
    aux
    0.78
    ality
    0.78
    perty
    0.77
     exceptions
    0.77
    Act Density 0.031%

    No Known Activations