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

    Neuronpedia

    INDEX
    Explanations

    instances of the document beginning or ending with a specific marker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BeginInit
    -0.62
     étoit
    -0.55
     ainfi
    -0.55
     siglas
    -0.51
     enfans
    -0.50
     feroit
    -0.50
     culturale
    -0.50
     auroit
    -0.50
     dévelo
    -0.48
     blancs
    -0.47
    POSITIVE LOGITS
    UserScript
    0.76
     فريبيس
    0.69
    Obrázky
    0.67
    Pautan
    0.67
    ]))
    0.66
    }")
    0.65
    RESUMEN
    0.65
     שוליים
    0.65
    ագրություններ
    0.65
    ollectionView
    0.63
    Act Density 0.033%

    No Known Activations