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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and" in various contexts

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endregion
    -0.50
    共に
    -0.49
     kanssa
    -0.48
     assuming
    -0.47
     ساتھ
    -0.47
     navideña
    -0.46
    ともに
    -0.46
     mukana
    -0.45
     bringing
    -0.45
     tartalomajánló
    -0.44
    POSITIVE LOGITS
    SerializedSize
    0.41
    +#+
    0.38
    Népesség
    0.38
     Stick
    0.38
    hability
    0.37
    kapp
    0.37
     ought
    0.35
    よかった
    0.35
     estekak
    0.35
     EconPapers
    0.34
    Act Density 0.108%

    No Known Activations