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

    Neuronpedia

    INDEX
    Explanations

    the preposition 'below' followed by a reference to a quantity or standard

    oai_token-act-pair · gpt-4-turbo

    values below a certain threshold

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical thresholds and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.74
    MM
    -0.72
    Mail
    -0.69
    Choice
    -0.69
     Outbreak
    -0.69
    Sense
    -0.68
    Counter
    -0.67
    RAW
    -0.67
    Translation
    -0.65
    Latin
    -0.65
    POSITIVE LOGITS
     carbohyd
    0.85
    eatures
    0.84
    ceed
    0.81
    graded
    0.77
    gradient
    0.75
    grading
    0.74
    grades
    0.72
     heights
    0.71
    uckland
    0.71
    cair
    0.70
    Act Density 0.034%

    No Known Activations