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

    Neuronpedia

    INDEX
    Explanations

    philosophical concepts related to truth and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Benton
    -0.15
     Geographic
    -0.14
    IRQ
    -0.14
    .enum
    -0.13
     Ukraj
    -0.13
    axter
    -0.13
    à¤Łà¤ķ
    -0.13
    campo
    -0.13
     Connecticut
    -0.13
    _literals
    -0.13
    POSITIVE LOGITS
     Dion
    0.42
     Nietzsche
    0.38
     Zar
    0.32
     Niet
    0.30
     Wagner
    0.28
     nihil
    0.25
     Apollo
    0.25
     Zeus
    0.25
     Ap
    0.24
     Friedrich
    0.23
    Act Density 0.018%

    No Known Activations