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

    Neuronpedia

    INDEX
    Explanations

    references to vampires and their associated characteristics in films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Autism
    -0.16
     autistic
    -0.16
     autism
    -0.16
    _px
    -0.15
    CACHE
    -0.15
    achu
    -0.15
    üz
    -0.14
    .Automation
    -0.14
     Corpor
    -0.14
    адж
    -0.14
    POSITIVE LOGITS
     vampire
    0.45
     vamp
    0.43
     Vampire
    0.42
     vampires
    0.41
    acula
    0.31
     wer
    0.29
    ampire
    0.28
     blood
    0.27
     Vlad
    0.26
     Buffy
    0.25
    Act Density 0.071%

    No Known Activations