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

    Neuronpedia

    INDEX
    Explanations

    references to training, combat, and psychological manipulation, particularly in a military or covert operations context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.73
    accharides
    -0.66
     Wonders
    -0.66
    NOPQRST
    -0.62
    ChildScrollView
    -0.61
    ãng
    -0.60
     elefante
    -0.58
     ArrayAdapter
    -0.58
    hoga
    -0.58
    RegistryLite
    -0.58
    POSITIVE LOGITS
     vengeance
    0.78
     ferocious
    0.76
     ruthless
    0.74
     brutality
    0.68
     Vengeance
    0.68
     brutal
    0.68
     fierce
    0.67
     lethal
    0.67
     edgy
    0.66
     fero
    0.66
    Act Density 0.682%

    No Known Activations