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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and temporal markers indicating sequence and timing in events

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

    linking phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $_(
    -0.73
    يكب
    -0.72
    ۠
    -0.67
    ｠
    -0.67
     nakalista
    -0.67
     ſehr
    -0.67
    ❳
    -0.67
    linawan
    -0.66
     geſch
    -0.65
     Lufthansa
    -0.65
    POSITIVE LOGITS
     emperador
    0.40
     lisäksi
    0.40
    If
    0.36
     šķ
    0.35
    In
    0.33
     érde
    0.33
    This
    0.33
    The
    0.33
    Therefore
    0.33
    What
    0.32
    Act Density 0.260%

    No Known Activations