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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and interactions between people

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

    "side" after certain prepositions or quantifiers

    np_acts-logits-general · gemini-2.0-flash

    other side or one side

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.45
    をも
    -0.42
    avut
    -0.39
    ographe
    -0.38
    辱
    -0.37
    jstor
    -0.36
     بهم
    -0.36
    Separator
    -0.36
     Abstand
    -0.36
     Roumanie
    -0.35
    POSITIVE LOGITS
     side
    2.86
     sides
    2.55
     Side
    2.45
    Side
    2.36
    side
    2.34
     SIDE
    2.32
    SIDE
    2.23
    sides
    2.13
     Sides
    2.05
    Sides
    1.95
    Act Density 0.423%

    No Known Activations