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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the existence or validity of claims and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rito
    -0.19
    eree
    -0.18
    orget
    -0.17
    353
    -0.16
    íĨµ
    -0.15
     Bilim
    -0.15
    occo
    -0.14
    [sizeof
    -0.14
    953
    -0.14
    _visitor
    -0.14
    POSITIVE LOGITS
     judge
    0.20
     Judge
    0.20
     Robertson
    0.18
     Judicial
    0.17
    Judge
    0.17
     ruling
    0.17
     judges
    0.17
    judge
    0.16
    axter
    0.16
    Jud
    0.15
    Act Density 0.020%

    No Known Activations