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

    Neuronpedia

    INDEX
    Explanations

    references to scientific research and its findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ansi
    -0.15
     Blocks
    -0.15
    esser
    -0.15
     blocks
    -0.15
    magic
    -0.14
    annel
    -0.14
     Magic
    -0.14
     Fishing
    -0.14
     Mist
    -0.14
     Des
    -0.14
    POSITIVE LOGITS
    ardy
    0.17
    ειÏĤ
    0.16
    afil
    0.15
    esture
    0.15
    onomy
    0.15
    /question
    0.15
    oid
    0.15
    bo
    0.14
    èĭ
    0.14
     ste
    0.14
    Act Density 0.008%

    No Known Activations