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

    Neuronpedia

    INDEX
    Explanations

    words associated with villains and their schemes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walkover
    -0.66
     समीक्षक
    -0.61
     contextos
    -0.52
    dziew
    -0.51
    coque
    -0.50
     forti
    -0.50
    intios
    -0.50
     Bourgoin
    -0.49
    こち
    -0.49
    上下文
    -0.48
    POSITIVE LOGITS
     evil
    0.75
    MLLoader
    0.68
    evil
    0.65
    Evil
    0.65
     OMITBAD
    0.64
     villain
    0.60
     wicked
    0.59
     Evil
    0.57
     actionTypes
    0.57
    ⓧ
    0.56
    Act Density 0.402%

    No Known Activations