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

    Neuronpedia

    INDEX
    Explanations

    references to zombies in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ional
    -0.92
    agall
    -0.83
    sers
    -0.82
    alties
    -0.81
    ours
    -0.80
    inion
    -0.78
    İ
    -0.77
    son
    -0.74
    orney
    -0.74
    itudes
    -0.73
    POSITIVE LOGITS
     apocalypse
    1.28
     Apocalypse
    1.07
     horde
    1.06
     hordes
    0.96
     outbreak
    0.89
    ombies
    0.89
     menace
    0.86
     zombie
    0.85
     virus
    0.85
     scourge
    0.85
    Act Density 0.030%

    No Known Activations