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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating obviousness or clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nown
    -0.18
    elon
    -0.17
    elman
    -0.16
    ocked
    -0.16
    plemented
    -0.16
    絶
    -0.15
    hape
    -0.14
    ropoda
    -0.14
    pty
    -0.14
    ————————
    -0.14
    POSITIVE LOGITS
    unction
    0.17
    517
    0.15
    afi
    0.14
    !=(
    0.14
    Æ¡n
    0.14
    afd
    0.14
     Gunn
    0.13
    enus
    0.13
     ours
    0.13
    uro
    0.13
    Act Density 0.058%

    No Known Activations