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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or conjunctions in the text, particularly "and."

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

    years between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noires
    -0.49
    msgTypes
    -0.46
    RuleContext
    -0.45
     båda
    -0.45
    InputBorder
    -0.44
     complémentaires
    -0.44
    şört
    -0.44
     besök
    -0.43
    睁开
    -0.43
     öppna
    -0.43
    POSITIVE LOGITS
     years
    0.77
     year
    0.63
    orianCalendar
    0.58
     months
    0.57
    VersionUID
    0.57
     Jahre
    0.56
    years
    0.56
     Jahren
    0.55
    Año
    0.55
     during
    0.54
    Act Density 0.024%

    No Known Activations