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

    Neuronpedia

    INDEX
    Explanations

    references to statistics or numerical data related to crime or law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburg
    -0.99
    wagen
    -0.84
    andowski
    -0.76
    ding
    -0.73
    theless
    -0.72
    ãĥĦ
    -0.72
    ffield
    -0.69
    ricting
    -0.68
    sch
    -0.67
    nesota
    -0.67
    POSITIVE LOGITS
    CI
    0.93
    PS
    0.89
    UTION
    0.89
    BIL
    0.86
    ERA
    0.86
    WS
    0.85
    KE
    0.85
    ELS
    0.83
    CE
    0.83
    ATES
    0.80
    Act Density 0.002%

    No Known Activations