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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic exams and test scores

    oai_token-act-pair · gpt-3.5-turbo

    references to standardized testing or educational assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.86
    hold
    -0.79
    ufact
    -0.76
    cies
    -0.74
    inen
    -0.73
    deals
    -0.67
     Samoa
    -0.63
    tymology
    -0.63
    lla
    -0.62
     moot
    -0.61
    POSITIVE LOGITS
    SE
    0.85
    ATS
    0.83
    ARD
    0.81
    asper
    0.81
    GC
    0.79
    ategory
    0.78
    raphic
    0.78
    ross
    0.76
    ogs
    0.76
    INTON
    0.74
    Act Density 0.030%

    No Known Activations