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

    Neuronpedia

    INDEX
    Explanations

    numeric sequences or formatted phone numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.15
     mor
    -0.15
     Mor
    -0.14
     bomb
    -0.14
    armor
    -0.14
     ceremon
    -0.13
     Bom
    -0.13
    å±ŀ
    -0.13
     Reconstruction
    -0.13
    rema
    -0.13
    POSITIVE LOGITS
    lier
    0.15
    initializer
    0.15
     Coch
    0.14
    orget
    0.14
    ?}",
    0.14
    poÄį
    0.14
    Ñıг
    0.13
     Jay
    0.13
    UNUSED
    0.13
    traction
    0.13
    Act Density 0.013%

    No Known Activations