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

    Neuronpedia

    INDEX
    Explanations

    references to research and development metrics or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĺŃ
    -0.15
    ourg
    -0.15
    Ñħод
    -0.14
    uger
    -0.14
    .k
    -0.14
    ngle
    -0.14
    tures
    -0.14
    åī
    -0.13
    å
    -0.13
    841
    -0.13
    POSITIVE LOGITS
    &
    0.40
    ï¼Ĩ
    0.30
    -&
    0.30
    &amp
    0.29
    &_
    0.29
     &
    0.29
    &&
    0.28
    &D
    0.28
    &↵
    0.28
    (&
    0.28
    Act Density 0.019%

    No Known Activations