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

    Neuronpedia

    INDEX
    Explanations

    references to nuclear weapons and articles discussing their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etc
    -0.19
     etc
    -0.15
    if
    -0.13
    ãģ§ãģ¯ãģªãģı
    -0.13
    yes
    -0.13
    orr
    -0.13
     Causes
    -0.13
     chứ
    -0.13
    ava
    -0.13
    1
    -0.13
    POSITIVE LOGITS
     how
    0.37
     related
    0.27
    how
    0.27
     ways
    0.27
     their
    0.27
     its
    0.26
     associated
    0.24
     cómo
    0.23
     attendant
    0.22
     resultant
    0.22
    Act Density 0.344%

    No Known Activations