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

    Neuronpedia

    INDEX
    Explanations

    references to werewolves and transformations

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

    werewolf, wolf, shapeshifter, druid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.47
     gorra
    -0.41
     viñ
    -0.38
     nät
    -0.36
     intelig
    -0.35
    ็จ
    -0.35
    vgili
    -0.34
     religione
    -0.34
     vivido
    -0.33
     portata
    -0.33
    POSITIVE LOGITS
     werewolf
    0.85
    wolves
    0.63
    wolf
    0.57
     wolf
    0.56
    TagMode
    0.54
     gynhyrchwyd
    0.51
     Druid
    0.50
     wolves
    0.49
    Druid
    0.49
     Lupus
    0.48
    Act Density 0.067%

    No Known Activations