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

    Neuronpedia

    INDEX
    Explanations

    comparisons or thresholds indicated by numerical values or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ball
    -1.85
    éric
    -1.67
    neh
    -1.48
    ...]
    -1.47
    untu
    -1.45
    iddell
    -1.44
    deb
    -1.43
    ugu
    -1.40
    ambled
    -1.38
    reich
    -1.38
    POSITIVE LOGITS
     practical
    1.48
    atics
    1.45
    between
    1.45
    Ĩ
    1.42
    ¨
    1.38
    ľ
    1.36
    catal
    1.35
    Ļ
    1.35
    ¤
    1.33
    aging
    1.33
    Act Density 0.246%

    No Known Activations