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

    Neuronpedia

    INDEX
    Explanations

    references to suspenseful or thriller elements in media, particularly involving serial killers or dark themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eryl
    -0.15
     Lincoln
    -0.14
    bob
    -0.14
    Lin
    -0.14
    Physics
    -0.14
    ufen
    -0.14
    PHY
    -0.14
    ode
    -0.14
     bob
    -0.14
    .ml
    -0.13
    POSITIVE LOGITS
     Hann
    0.49
     Lect
    0.41
     hann
    0.35
     cann
    0.30
     Silence
    0.29
     Harris
    0.28
     Cann
    0.28
     lect
    0.27
     Mann
    0.26
     Clar
    0.25
    Act Density 0.001%

    No Known Activations