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

    Neuronpedia

    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and single quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensen
    -0.78
    manship
    -0.76
    isphere
    -0.70
    uto
    -0.67
    inals
    -0.66
     Meier
    -0.64
    ãĥĭ
    -0.63
     blow
    -0.62
    nown
    -0.61
    inki
    -0.61
    POSITIVE LOGITS
    Interstitial
    1.17
    Cause
    1.16
    cause
    1.07
     ',
    1.05
    taboola
    1.05
    tis
    0.95
    -'
    0.94
    Mech
    0.93
     '.
    0.85
    Course
    0.84
    Act Density 0.067%

    No Known Activations