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

    Neuronpedia

    INDEX
    Explanations

    data related to academic performance metrics and standardized test scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    tests and scores

    np_acts-logits-general · gemini-2.0-flash

    SAT score

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.65
    CrossRef
    -0.59
    HMIS
    -0.58
    balleur
    -0.56
    $_['
    -0.51
     RouterModule
    -0.51
    Initializable
    -0.50
     StringField
    -0.50
     propag
    -0.50
    bigr
    -0.48
    POSITIVE LOGITS
     score
    0.94
     scores
    0.93
     test
    0.90
     Scores
    0.86
     Test
    0.81
     Score
    0.81
     exam
    0.81
     scoring
    0.81
     scored
    0.80
     scorers
    0.80
    Act Density 0.148%

    No Known Activations