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

    Neuronpedia

    INDEX
    Explanations

    phrases that start with "So."

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

    introductory so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stamp
    -0.41
     Stamp
    -0.40
     Machinery
    -0.36
    penet
    -0.36
     Localized
    -0.36
    Localized
    -0.35
    linen
    -0.35
    Mach
    -0.35
    amarca
    -0.35
    elev
    -0.34
    POSITIVE LOGITS
    So
    0.83
     So
    0.66
    Итак
    0.63
     Wikiseite
    0.61
    Sooo
    0.58
     Donc
    0.57
     ویکی‌پدیای
    0.57
    mybatisplus
    0.57
    SequentialGroup
    0.54
    Donc
    0.54
    Act Density 0.017%

    No Known Activations