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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references to statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nov
    -0.16
     Nov
    -0.16
     August
    -0.15
    Nov
    -0.14
    ellation
    -0.14
    ulin
    -0.13
    ãĤīãģĽ
    -0.13
     nova
    -0.13
    utsch
    -0.13
    August
    -0.13
    POSITIVE LOGITS
     Ten
    0.98
     ten
    0.94
    10
    0.91
    Ten
    0.87
     TEN
    0.84
    _ten
    0.79
    åįģ
    0.78
    ten
    0.77
     tenth
    0.70
    Û±Û°
    0.62
    Act Density 0.410%

    No Known Activations