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

    Neuronpedia

    INDEX
    Explanations

    references to the creation or production of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.16
    uddy
    -0.16
    fully
    -0.15
    iard
    -0.15
    lessly
    -0.14
    845
    -0.14
     thereof
    -0.14
    ably
    -0.14
    compat
    -0.14
    aux
    -0.14
    POSITIVE LOGITS
    ness
    0.20
    /shared
    0.19
    /generated
    0.19
    atum
    0.18
     porr
    0.17
    OCUMENT
    0.17
    /cop
    0.17
    /upload
    0.16
    _at
    0.15
    :
    0.15
    Act Density 0.195%

    No Known Activations