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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters or law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    the article "an."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Things
    -0.73
    bots
    -0.72
    cules
    -0.71
    bane
    -0.69
    ï¸
    -0.68
    ðŁij
    -0.68
     Turns
    -0.67
    Allow
    -0.67
    Changes
    -0.67
     Vaugh
    -0.66
    POSITIVE LOGITS
    esthetic
    1.06
    omal
    0.87
     bunch
    0.75
     glimpse
    0.75
    ormal
    0.75
    abolic
    0.73
     sizeable
    0.73
     huge
    0.73
    sexual
    0.73
    ufact
    0.72
    Act Density 0.200%

    No Known Activations