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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating action or change in state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    292
    -0.16
    757
    -0.15
    ceiver
    -0.15
    phans
    -0.14
    uy
    -0.14
    skyt
    -0.13
    lech
    -0.13
    nuts
    -0.13
    ernote
    -0.13
    entials
    -0.13
    POSITIVE LOGITS
    ednou
    0.20
    oad
    0.16
     Benson
    0.15
    840
    0.14
    HAS
    0.14
    cka
    0.14
    @qq
    0.14
     Pear
    0.13
     Factory
    0.13
     Farr
    0.13
    Act Density 0.406%

    No Known Activations