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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and logical structures within sentences

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

    punctuation followed by consequential words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.48
     AssemblyCompany
    -0.40
    rawDesc
    -0.39
    Gill
    -0.38
    SequentialGroup
    -0.36
     Gill
    -0.36
    hyrchwyd
    -0.36
    몰
    -0.34
    (!__
    -0.34
    生意
    -0.34
    POSITIVE LOGITS
    RegressionTest
    0.55
    Genau
    0.52
     <<<<<<<<<<<<<<
    0.51
     Einzelnen
    0.48
     مشين
    0.46
     ब्रेकडाउन
    0.45
     desirability
    0.45
    JAKARTA
    0.44
    enumi
    0.43
     Genau
    0.43
    Act Density 0.447%

    No Known Activations