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

    Neuronpedia

    INDEX
    Explanations

    statements made by individuals, particularly in the context of quotes or attributions

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

    Attributions of quotes

    np_acts-logits-general · gemini-2.0-flash

    attributed speech and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.60
    Portale
    -0.50
    تقاوى
    -0.48
    ➯
    -0.48
    HandlerContext
    -0.48
     beginnetje
    -0.48
    Tikang
    -0.46
    ]=>
    -0.45
     BorderSide
    -0.45
    Ӕ
    -0.44
    POSITIVE LOGITS
     speech
    0.52
     saying
    0.52
    脚注の使い方
    0.49
     spoken
    0.49
     spoke
    0.49
    AccessorTable
    0.48
     speeches
    0.48
     speaking
    0.47
     quoted
    0.42
     expressed
    0.42
    Act Density 0.165%

    No Known Activations