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

    Neuronpedia

    INDEX
    Explanations

    references to films or content related to comedy, specifically those involving ghosts or supernatural themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.16
    ique
    -0.16
     Dah
    -0.15
    élé
    -0.15
     Leaf
    -0.15
     Hart
    -0.14
     jew
    -0.14
    UDA
    -0.14
     flags
    -0.14
    loh
    -0.14
    POSITIVE LOGITS
    Ghost
    0.34
     Ghost
    0.34
     ghost
    0.29
    _ghost
    0.29
     proton
    0.27
    ghost
    0.27
     ghosts
    0.26
    busters
    0.23
    éľĬ
    0.19
     paranormal
    0.19
    Act Density 0.003%

    No Known Activations