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

    Neuronpedia

    INDEX
    Explanations

    iterative transformations or conversions of concepts into different forms or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saites
    -0.56
    AutoScale
    -0.48
    konomi
    -0.48
    LabelTagHelper
    -0.47
    SequentialGroup
    -0.47
    المشاركات
    -0.47
    AutoScaleMode
    -0.46
    Географиясе
    -0.46
    careous
    -0.46
     Salamanca
    -0.45
    POSITIVE LOGITS
     превра
    0.64
     تبدیل
    0.61
     Become
    0.59
     BECOME
    0.58
     becoming
    0.56
     become
    0.56
     verwan
    0.56
    Become
    0.56
     becomes
    0.55
    变成
    0.55
    Act Density 0.569%

    No Known Activations