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

    Neuronpedia

    INDEX
    Explanations

    references to villains and their characteristics in media narratives

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

    villain and enemy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stdc
    -0.48
     Signalez
    -0.47
     Eren
    -0.45
    Personensuche
    -0.44
    InputTagHelper
    -0.44
     detailsLots
    -0.44
    aarrggbb
    -0.43
     estekak
    -0.43
    #+#
    -0.42
    السكان
    -0.42
    POSITIVE LOGITS
     villains
    0.63
     villain
    0.58
     antagonist
    0.55
    villain
    0.53
     antagonists
    0.50
    Personendaten
    0.48
     musuh
    0.46
     Gegner
    0.45
     Villain
    0.44
     nemesis
    0.44
    Act Density 0.161%

    No Known Activations