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

    Neuronpedia

    INDEX
    Explanations

    references to castles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mahomet
    -0.70
    اعمال
    -0.68
    _^
    -0.65
     Yoh
    -0.64
     CWE
    -0.63
    liel
    -0.63
    wpi
    -0.63
    __':
    -0.62
    ại
    -0.62
     internetowa
    -0.61
    POSITIVE LOGITS
     Castle
    0.95
     castle
    0.84
     mansion
    0.83
     Duff
    0.82
    RICULUM
    0.80
     Castles
    0.78
     Mansion
    0.77
     CASTLE
    0.74
     Curriculum
    0.74
    curriculum
    0.73
    Act Density 0.206%

    No Known Activations