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

    Neuronpedia

    INDEX
    Explanations

    references to blades used in various contexts, particularly surgical and mechanical applications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     overras
    -0.84
     SHR
    -0.76
     Finley
    -0.71
    nito
    -0.71
     Pequ
    -0.71
    Carreira
    -0.69
     Harlow
    -0.68
     coppia
    -0.67
     PRC
    -0.66
    cotch
    -0.66
    POSITIVE LOGITS
     blades
    1.83
     blade
    1.63
     Blades
    1.60
    blades
    1.50
     Blade
    1.46
    blade
    1.43
    Blade
    1.27
     sword
    0.99
     swords
    0.93
     Sword
    0.89
    Act Density 0.007%

    No Known Activations