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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a dependence or significance related to some condition or context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "without."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mers
    -0.78
    des
    -0.77
    estate
    -0.70
     Inquisition
    -0.70
    emetery
    -0.68
    oola
    -0.68
    etimes
    -0.68
    dozen
    -0.67
    mun
    -0.67
    ocations
    -0.67
    POSITIVE LOGITS
     regard
    0.81
     knowing
    0.76
     exception
    0.73
     blinking
    0.68
     mentioning
    0.67
     assuming
    0.66
     doubt
    0.66
    lessly
    0.65
     hesitation
    0.65
     Borders
    0.64
    Act Density 0.029%

    No Known Activations