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

    Neuronpedia

    INDEX
    Explanations

    expressions of frustration or discontent in social interactions

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

    kid, dad, sap, pop, picnic, phony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ifiquement
    -0.38
     øns
    -0.35
     comprendere
    -0.34
     Substanz
    -0.34
     endast
    -0.33
     protocolo
    -0.33
    EndInit
    -0.32
     tatsäch
    -0.32
     murni
    -0.32
    ค่ะ
    -0.31
    POSITIVE LOGITS
    tough
    0.63
    quelize
    0.61
     fellas
    0.58
     الرياضيه
    0.56
     Tough
    0.52
    PARATUS
    0.52
    CheckBreak
    0.52
     שוליים
    0.51
    最快更新
    0.51
     Dete
    0.50
    Act Density 0.299%

    No Known Activations