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

    Neuronpedia

    INDEX
    Explanations

    references to different types of casts, particularly in relation to iron and metal

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

    "Cast" and variations

    np_acts-logits-general · gemini-2.0-flash

    cast iron, metal, and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SwitchCompat
    -1.01
     Мексичка
    -0.99
     itſelf
    -0.94
    ſelf
    -0.94
    riwal
    -0.94
    ViewFeatures
    -0.92
    ſelves
    -0.91
     }}"></
    -0.91
     leſs
    -0.91
     pleaſure
    -0.90
    POSITIVE LOGITS
     Cast
    1.27
    Cast
    1.08
     cast
    1.04
     CAST
    1.01
    cast
    0.89
     casts
    0.87
     Kast
    0.86
    CAST
    0.80
     kast
    0.78
     casting
    0.77
    Act Density 0.051%

    No Known Activations