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

    Neuronpedia

    INDEX
    Explanations

    references to deputy positions or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mach
    -0.16
    наÑĢ
    -0.16
    cheid
    -0.15
    mina
    -0.15
    argin
    -0.15
     пÑĢа
    -0.14
    nar
    -0.14
    arg
    -0.14
    rad
    -0.14
     sÃłng
    -0.14
    POSITIVE LOGITS
    ville
    0.18
    602
    0.16
    dogs
    0.15
    ure
    0.14
    _gold
    0.14
     Dro
    0.14
    ppers
    0.14
     Bale
    0.13
    oco
    0.13
    321
    0.13
    Act Density 0.006%

    No Known Activations