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

    Neuronpedia

    INDEX
    Explanations

    repetitive expressions and informal phrases in conversation

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

    や or いや

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hilsen
    -0.42
     beslut
    -0.40
     majeure
    -0.38
     ListTile
    -0.37
    ciutto
    -0.37
    bison
    -0.36
    Lumi
    -0.36
    {}",
    -0.35
     mosa
    -0.35
    SPOILER
    -0.35
    POSITIVE LOGITS
    や
    1.53
     や
    1.05
    이나
    1.00
    やお
    0.94
     or
    0.87
    んや
    0.77
     či
    0.74
    或
    0.73
    んだり
    0.73
     maupun
    0.72
    Act Density 0.002%

    No Known Activations