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

    Neuronpedia

    INDEX
    Explanations

    references to specific fantasy or supernatural creatures, particularly vampires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .AutoComplete
    -0.17
    ixel
    -0.15
    abee
    -0.15
     autistic
    -0.14
    CACHE
    -0.14
    212
    -0.14
     Gaul
    -0.14
     VOID
    -0.14
    .MSG
    -0.14
    oden
    -0.14
    POSITIVE LOGITS
     vampire
    0.44
     vampires
    0.42
     vamp
    0.42
     Vampire
    0.41
    acula
    0.31
     wer
    0.30
    ampire
    0.29
     bats
    0.27
     bat
    0.27
    Wer
    0.26
    Act Density 0.033%

    No Known Activations