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

    Neuronpedia

    INDEX
    Explanations

    terms associated with penalties and criminal justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ように
    -0.77
    less
    -0.54
    ly
    -0.48
    literature
    -0.46
     contemporaine
    -0.44
    ٔ
    -0.44
     aérienne
    -0.42
    lerini
    -0.42
     mourir
    -0.41
     ciudadana
    -0.40
    POSITIVE LOGITS
    ized
    1.02
    ization
    0.86
    izing
    0.85
    ize
    0.84
    istic
    0.81
    izations
    0.80
    ists
    0.76
    dehyde
    0.75
    isation
    0.72
    izes
    0.71
    Act Density 1.292%

    No Known Activations