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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

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

    who was in his sole custody

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    发表于
    -0.43
    oa̍t
    -0.41
    ":["
    -0.40
    :].
    -0.40
    Халык
    -0.40
    "]))
    -0.39
    arXiv
    -0.39
    цездатний
    -0.39
    كويكب
    -0.38
    ()?;
    -0.37
    POSITIVE LOGITS
     سكانية
    0.57
     scattata
    0.54
    ledem
    0.52
    kusen
    0.50
    AxisAlignment
    0.50
     informée
    0.50
    StructEnd
    0.49
     selaku
    0.49
     relógio
    0.47
    elcome
    0.46
    Act Density 0.050%

    No Known Activations