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

    Neuronpedia

    INDEX
    Explanations

    tokens related to numerical values and formatting in text

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

    user utterances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.47
    InstrumentedTest
    -0.46
    parsedMessage
    -0.46
    writeFieldEnd
    -0.42
    цездатний
    -0.41
    anglès
    -0.40
     дописавши
    -0.39
    UrlResolution
    -0.38
     nahilalakip
    -0.38
    󠁴
    -0.35
    POSITIVE LOGITS
    HandlerContext
    0.51
    蚪
    0.48
    charest
    0.42
    
    0.42
    ]=>
    0.41
    <bos>
    0.41
     ostavi
    0.41
    riwal
    0.41
     hinein
    0.41
     mostrarán
    0.41
    Act Density 0.000%

    No Known Activations