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

    Neuronpedia

    INDEX
    Explanations

    references to a virus or epidemic-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (~(
    -0.15
    arrass
    -0.15
    adal
    -0.14
     doma
    -0.14
     Assass
    -0.14
     Assassin
    -0.14
     Cyr
    -0.14
    Ĺ
    -0.14
    trak
    -0.14
    opot
    -0.14
    POSITIVE LOGITS
     zombie
    0.39
     zombies
    0.36
     survivors
    0.35
     infected
    0.35
     Zombie
    0.34
     Zombies
    0.34
     survivor
    0.32
     infection
    0.30
     Surv
    0.29
     apocalypse
    0.29
    Act Density 0.121%

    No Known Activations