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

    Neuronpedia

    INDEX
    Explanations

    references to violence in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.64
     vôtre
    -0.59
    OGND
    -0.53
     yourselves
    -0.51
    openzeppelin
    -0.51
    AsUp
    -0.50
    ยว
    -0.49
     TODAY
    -0.49
     today
    -0.48
    SourceChecksum
    -0.47
    POSITIVE LOGITS
     symbolizes
    1.03
     simbo
    1.00
     symbolically
    0.99
     symbolized
    0.99
     symbolize
    0.94
     symboli
    0.94
     narrator
    0.92
     symbolic
    0.90
     foreshadow
    0.89
     represents
    0.86
    Act Density 0.455%

    No Known Activations