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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or reasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.75
     Cæsar
    -0.74
     Efq
    -0.73
     himſelf
    -0.71
     Theſe
    -0.70
     quæ
    -0.67
     myſelf
    -0.66
     ogóle
    -0.64
     equilateral
    -0.62
    unächst
    -0.61
    POSITIVE LOGITS
    Because
    1.06
     owing
    1.04
     Because
    0.99
    Due
    0.97
     Owing
    0.97
    because
    0.96
     karena
    0.96
    Debido
    0.95
     because
    0.94
     due
    0.94
    Act Density 0.208%

    No Known Activations