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

    Neuronpedia

    INDEX
    Explanations

    instances of slashes in text, possibly indicating separations or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    slash separated lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.61
     feroit
    -0.59
     pouvoit
    -0.57
     avoient
    -0.55
     auroit
    -0.52
     mauva
    -0.50
     plufieurs
    -0.47
     étoient
    -0.46
     étoit
    -0.44
    klart
    -0.41
    POSITIVE LOGITS
     /
    1.96
    ／
    1.19
    /
    1.16
    '/
    1.12
    `/
    1.12
     '/
    1.10
     (/
    1.09
     /$
    1.09
    |/
    1.09
    (/
    1.09
    Act Density 0.012%

    No Known Activations