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

    Neuronpedia

    INDEX
    Explanations

    themes related to dark and crime-related narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interval
    -0.15
    avras
    -0.15
     Sequ
    -0.15
    logan
    -0.15
    throp
    -0.14
     Hedge
    -0.14
    idente
    -0.14
     Pars
    -0.14
    cott
    -0.14
     Sous
    -0.14
    POSITIVE LOGITS
     noir
    0.33
     Noir
    0.31
     Femme
    0.24
     femme
    0.24
     pulp
    0.23
     dames
    0.23
     hard
    0.22
     tough
    0.21
     crime
    0.21
     PI
    0.21
    Act Density 0.032%

    No Known Activations