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

    Neuronpedia

    INDEX
    Explanations

    references to horror, especially in the context of literature and film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     referenties
    -0.80
     ویکی‌پدی
    -0.78
    thâu
    -0.74
    otide
    -0.70
     gawas
    -0.68
    ]<=
    -0.63
     indisponible
    -0.63
    ########.
    -0.63
    Att
    -0.62
     Att
    -0.61
    POSITIVE LOGITS
    dy
    1.22
     dy
    0.89
    Dy
    0.89
    DY
    0.87
     Dy
    0.84
     speculation
    0.75
     speculative
    0.72
     speculating
    0.72
     rumours
    0.69
     hopeful
    0.68
    Act Density 0.154%

    No Known Activations