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

    Neuronpedia

    INDEX
    Explanations

    words related to sharp objects, specifically knives

    oai_token-act-pair · gpt-3.5-turbo

    references to knives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mberg
    -0.86
    rian
    -0.82
    rians
    -0.81
    oday
    -0.78
    tainment
    -0.78
    rium
    -0.75
    ICLE
    -0.74
    ALS
    -0.72
    rix
    -0.71
     Emin
    -0.71
    POSITIVE LOGITS
     knives
    1.05
     knife
    1.02
    knife
    1.00
     blades
    0.99
     scissors
    0.98
     blade
    0.97
     slicing
    0.91
     cutter
    0.87
     wielding
    0.87
     claws
    0.86
    Act Density 0.025%

    No Known Activations