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

    Neuronpedia

    INDEX
    Explanations

    references to horror films and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     diseñador
    -0.16
    viar
    -0.16
    ensch
    -0.15
     cond
    -0.15
    avr
    -0.15
    loh
    -0.15
    å¢ĵ
    -0.15
    nage
    -0.14
    боÑĤ
    -0.14
     morb
    -0.14
    POSITIVE LOGITS
     Saw
    0.21
     possession
    0.19
     Blair
    0.19
     Conj
    0.19
     possessed
    0.18
     Poss
    0.17
     Candy
    0.17
    itty
    0.16
     Clover
    0.16
    poss
    0.16
    Act Density 0.030%

    No Known Activations