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

    Neuronpedia

    INDEX
    Explanations

    statistics or facts presented in a format of 'out of a given number'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate statistical data or proportions related to groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arsen
    -0.78
    abilia
    -0.64
    antry
    -0.64
     capt
    -0.62
    wake
    -0.61
    kefeller
    -0.61
     Vas
    -0.60
     Lives
    -0.60
    icultural
    -0.60
     grooming
    -0.59
    POSITIVE LOGITS
    dated
    0.85
    stretched
    0.81
    lier
    0.81
    fitted
    0.79
    number
    0.76
    landers
    0.73
    )=(
    0.72
    rists
    0.72
    enth
    0.71
    numbered
    0.70
    Act Density 0.017%

    No Known Activations