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

    Neuronpedia

    INDEX
    Explanations

    mathematical or programming equations and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prec
    -0.17
    ãĥ³ãĤ¬
    -0.16
    aign
    -0.15
    unga
    -0.14
    ble
    -0.14
    ugo
    -0.14
    aurus
    -0.14
    ̧
    -0.14
    acks
    -0.13
    andin
    -0.13
    POSITIVE LOGITS
    NSSet
    0.16
    VES
    0.15
    uky
    0.15
    enor
    0.15
     argument
    0.15
     Bray
    0.15
    uds
    0.14
    çķ
    0.14
    ency
    0.14
    jon
    0.14
    Act Density 0.200%

    No Known Activations