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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence and academic performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gross
    -0.20
     gross
    -0.18
     Gross
    -0.15
    rek
    -0.15
    ichern
    -0.15
    eda
    -0.15
    olumn
    -0.15
    sizeof
    -0.14
    Intensity
    -0.14
    FirstResponder
    -0.14
    POSITIVE LOGITS
     score
    0.34
     scores
    0.27
    _score
    0.25
     Score
    0.25
    -score
    0.24
     Scores
    0.24
    Score
    0.23
    score
    0.23
    Scores
    0.22
    .score
    0.22
    Act Density 0.106%

    No Known Activations