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

    Neuronpedia

    INDEX
    Explanations

    specific years mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    mention of the year 1995 and its surrounding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    suit
    -0.77
    mic
    -0.73
    iard
    -0.73
    ming
    -0.71
    adesh
    -0.71
    phas
    -0.71
    gie
    -0.70
    horse
    -0.70
    wards
    -0.69
    pressure
    -0.69
    POSITIVE LOGITS
    %:
    0.83
    uously
    0.83
    ulum
    0.79
    uation
    0.75
    aneously
    0.71
    isher
    0.70
     kHz
    0.69
    aneous
    0.68
    rican
    0.67
    RET
    0.66
    Act Density 0.049%

    No Known Activations