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

    Neuronpedia

    INDEX
    Explanations

    references to official decisions or requests related to policy matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ác
    -0.15
    оваÑĢ
    -0.14
    ati
    -0.14
    λλ
    -0.14
    declare
    -0.14
     Offices
    -0.13
     Spiral
    -0.13
    w
    -0.13
     Bros
    -0.13
    gi
    -0.13
    POSITIVE LOGITS
    esto
    0.17
    egasus
    0.15
     to
    0.15
     bahwa
    0.15
    unication
    0.14
    ekt
    0.14
    aines
    0.14
    ichel
    0.14
    andex
    0.14
    /request
    0.14
    Act Density 0.123%

    No Known Activations