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

    Neuronpedia

    INDEX
    Explanations

    references to specific medical conditions and treatment-related terminology

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     Cad
    -1.20
    Cad
    -0.98
     cad
    -0.84
     cadre
    -0.80
     cadence
    -0.75
     cadres
    -0.70
    cadre
    -0.61
     '\\;'
    -0.58
    cault
    -0.55
     SES
    -0.53
    POSITIVE LOGITS
     CAD
    1.81
    CAD
    1.38
    MLLoader
    0.76
    GenerationType
    0.65
     couteau
    0.63
    InitVars
    0.63
    PROMOTED
    0.62
    HostException
    0.60
     <=",
    0.60
     paille
    0.58
    Act Density 0.001%

    No Known Activations