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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activities or legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to criminal activities or charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -1.02
    daq
    -0.82
    pread
    -0.82
    chell
    -0.80
     Remastered
    -0.80
    metry
    -0.79
    mates
    -0.77
    pler
    -0.75
    blank
    -0.73
    galitarian
    -0.73
    POSITIVE LOGITS
    ized
    1.15
    izes
    1.06
    ization
    1.04
     justice
    1.00
    ised
    0.98
    izing
    0.98
     prosecutions
    0.96
     enterprises
    0.93
     mastermind
    0.92
    ising
    0.92
    Act Density 0.038%

    No Known Activations