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

    Neuronpedia

    INDEX
    Explanations

    different types of novels and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Custo
    -0.57
     Osiris
    -0.50
     cim
    -0.47
    Beaver
    -0.46
     castor
    -0.46
     grat
    -0.45
     Beaver
    -0.45
     rati
    -0.45
    Custo
    -0.45
     Disability
    -0.45
    POSITIVE LOGITS
     novel
    1.05
     novels
    1.00
    novel
    0.93
     romanzo
    0.92
     Novel
    0.92
     NOVEL
    0.88
    Novel
    0.85
     Novels
    0.84
     novelist
    0.80
     novelists
    0.78
    Act Density 0.214%

    No Known Activations