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

    Neuronpedia

    INDEX
    Explanations

    references to violence and physical weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    żesz
    -0.63
    Lähteet
    -0.59
    UnknownFieldSet
    -0.58
     Soares
    -0.56
    Carriera
    -0.55
    Tracce
    -0.55
    hoots
    -0.53
    achella
    -0.53
     Wallflower
    -0.53
    ніципа
    -0.53
    POSITIVE LOGITS
     blade
    1.12
     knife
    0.95
     blades
    0.89
     Blade
    0.85
     handle
    0.84
    Blade
    0.82
    blade
    0.81
     sheath
    0.79
     knives
    0.77
     Blades
    0.75
    Act Density 0.095%

    No Known Activations