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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate transitions or changes in state

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

    switch to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     affari
    -0.48
     שוליים
    -0.48
    LEGGI
    -0.47
     pungkasnya
    -0.47
    propy
    -0.47
    incontro
    -0.44
     tiroirs
    -0.44
     geométrico
    -0.43
     marbre
    -0.42
     jurídico
    -0.42
    POSITIVE LOGITS
    delwed
    0.56
    改为
    0.54
    oredCriteria
    0.50
    switchTo
    0.49
    UnusedPrivate
    0.46
    Autoritní
    0.44
     ganti
    0.43
     substituted
    0.43
    變成
    0.43
    变成
    0.43
    Act Density 0.043%

    No Known Activations