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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or special characters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    anyahu
    -0.88
     arşivlendi
    -0.86
    Christie
    -0.81
     SDLK
    -0.80
    (!__
    -0.79
     McNally
    -0.77
     linkovi
    -0.77
    FunctionFlags
    -0.77
     AssemblyTitle
    -0.77
     Hilde
    -0.77
    POSITIVE LOGITS
    °
    0.91
     Orrell
    0.69
    °°
    0.68
    tellung
    0.66
    ValueGeneration
    0.64
     ais
    0.64
     Armen
    0.64
    °)
    0.62
    ton
    0.61
    gang
    0.61
    Act Density 0.000%

    No Known Activations