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

    Neuronpedia

    INDEX
    Explanations

    narrative elements involving conflict or tension

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gustos
    -0.42
     domingos
    -0.34
     existed
    -0.33
     sobran
    -0.33
     рода
    -0.32
     lắm
    -0.32
     virtudes
    -0.32
    に関しては
    -0.32
     любое
    -0.31
     bete
    -0.30
    POSITIVE LOGITS
     flames
    0.98
     plumes
    0.95
     voices
    0.90
     screams
    0.90
     darkness
    0.89
     swarms
    0.88
     smoke
    0.87
     clouds
    0.87
     explosions
    0.86
     terdengar
    0.85
    Act Density 0.502%

    No Known Activations