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

    Neuronpedia

    INDEX
    Explanations

    references to physical blades, especially in contexts related to weaponry and tools

    oai_token-act-pair · gpt-3.5-turbo

    references to blades in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bos
    -0.79
    upon
    -0.78
    ordable
    -0.77
    odes
    -0.73
    dk
    -0.72
    obyl
    -0.72
    rouse
    -0.71
    ally
    -0.71
    ean
    -0.70
    ently
    -0.69
    POSITIVE LOGITS
     blades
    1.40
     blade
    1.31
    blade
    1.12
     Blade
    1.00
     Cutter
    0.95
     Blades
    0.94
    Blade
    0.92
    tips
    0.89
     knives
    0.89
     Runner
    0.86
    Act Density 0.010%

    No Known Activations