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

    Neuronpedia

    INDEX
    Explanations

    sentences that end with a punctuation mark or contain significant pauses in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eware
    -0.17
    YS
    -0.17
     hist
    -0.15
    znik
    -0.15
    ][(
    -0.15
    .JTable
    -0.14
    ware
    -0.14
    iri
    -0.14
    迹
    -0.14
    /native
    -0.14
    POSITIVE LOGITS
    ould
    0.14
    ersh
    0.14
    inea
    0.14
     settlements
    0.14
    odos
    0.14
     sing
    0.14
    buz
    0.14
    yb
    0.14
    ĭ
    0.13
    \<
    0.13
    Act Density 0.001%

    No Known Activations