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

    Neuronpedia

    INDEX
    Explanations

    instances of danger or threat in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sutton
    -0.19
    insky
    -0.17
    Ĺ
    -0.17
    ré
    -0.16
     Sez
    -0.15
    ISTA
    -0.15
     Assass
    -0.15
    chal
    -0.14
     genie
    -0.14
     Assassin
    -0.14
    POSITIVE LOGITS
     Romero
    0.36
     infected
    0.36
     zombies
    0.35
     zombie
    0.34
     infection
    0.32
     Zombies
    0.32
     undead
    0.32
    ombie
    0.30
     Zombie
    0.29
    ombies
    0.29
    Act Density 0.057%

    No Known Activations