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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate transformation or change

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

    become transforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contemporáneo
    -0.60
     responsabilità
    -0.54
     שוליים
    -0.52
     saites
    -0.52
     paja
    -0.51
     gql
    -0.51
     aguja
    -0.50
     Wahr
    -0.50
     contemporain
    -0.49
    majánló
    -0.49
    POSITIVE LOGITS
     become
    0.60
    变成
    0.58
    become
    0.58
     becomes
    0.56
     verwan
    0.56
    becomes
    0.55
     превра
    0.54
     transformed
    0.54
    變成
    0.54
     transforme
    0.53
    Act Density 0.014%

    No Known Activations