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

    Neuronpedia

    INDEX
    Explanations

    references to vampires and their interactions with humans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    vampires and their companions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     didst
    -0.57
     StringTokenizer
    -0.56
    BibitemShut
    -0.56
     informée
    -0.53
    bewerken
    -0.53
     inspir
    -0.53
    parsedMessage
    -0.52
     contextLoads
    -0.51
     pessi
    -0.51
     Scaffold
    -0.51
    POSITIVE LOGITS
     vampire
    0.59
     supernatural
    0.58
     centuries
    0.50
     werewolf
    0.49
    vampire
    0.48
     vampires
    0.46
     humans
    0.45
     coven
    0.43
     killings
    0.43
    humans
    0.43
    Act Density 0.085%

    No Known Activations