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

    Neuronpedia

    INDEX
    Explanations

    references to fiction and fictional works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    fiction genre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Anhalt
    -0.52
    AAA
    -0.49
    ARP
    -0.48
     “
    -0.47
    AN
    -0.47
    Are
    -0.46
     Schweitzer
    -0.46
     Manley
    -0.45
    Kyle
    -0.45
     U
    -0.45
    POSITIVE LOGITS
     fiction
    1.09
     Fiction
    1.05
     FICTION
    0.94
    Fiction
    0.93
    fiction
    0.90
     ficción
    0.85
     BoxDecoration
    0.73
    MLLoader
    0.71
    jface
    0.66
     Fic
    0.64
    Act Density 0.006%

    No Known Activations