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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflict and negotiation

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

    Follows a comma

    np_acts-logits-general · gemini-2.0-flash

    connecting conjunctions and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incentiv
    -0.74
    CloseOperation
    -0.64
    )?;
    -0.61
    脚注の使い方
    -0.59
    Rujuakan
    -0.58
     aka
    -0.57
    AKA
    -0.57
     prioritized
    -0.57
     showcased
    -0.56
    aka
    -0.56
    POSITIVE LOGITS
     läßt
    0.71
     ибо
    0.70
     Daß
    0.66
     daß
    0.65
    ReusableCell
    0.60
     circunstancia
    0.60
     quæ
    0.57
     bearing
    0.57
     wenigstens
    0.56
     numai
    0.56
    Act Density 0.329%

    No Known Activations