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

    Neuronpedia

    INDEX
    Explanations

    references to fiction or fictional works

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Muh
    -0.67
    GEBURTS
    -0.66
     Koenig
    -0.64
     Kase
    -0.64
     kysy
    -0.63
    Precautionary
    -0.63
    posia
    -0.63
    MessageOf
    -0.62
    atra
    -0.61
     Eich
    -0.61
    POSITIVE LOGITS
     fiction
    1.34
     Fiction
    1.32
     FICTION
    1.20
    Fiction
    1.15
     Fic
    1.03
    fiction
    1.00
    Fic
    1.00
     fictional
    0.97
     fic
    0.96
     ficción
    0.92
    Act Density 0.005%

    No Known Activations