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

    Neuronpedia

    INDEX
    Explanations

    references to machines and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.18
    ê¹
    -0.17
    lier
    -0.17
    mmo
    -0.17
    shire
    -0.17
    lyn
    -0.17
    theless
    -0.16
    cheme
    -0.16
    ric
    -0.15
    sson
    -0.15
    POSITIVE LOGITS
    -readable
    0.31
    gun
    0.29
    -gun
    0.27
     gun
    0.22
    guns
    0.21
    /software
    0.21
     readable
    0.21
     Gun
    0.20
    imals
    0.20
    parts
    0.19
    Act Density 0.022%

    No Known Activations