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

    Neuronpedia

    INDEX
    Explanations

    confirmations or affirmations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TResult
    -0.46
     dom
    -0.41
    MV
    -0.40
    怎
    -0.39
    Then
    -0.39
    Dom
    -0.39
     domain
    -0.38
    then
    -0.38
     Then
    -0.36
    uh
    -0.36
    POSITIVE LOGITS
    GEBURTSDATUM
    0.93
     calendriers
    0.89
    ViewImports
    0.89
     autorytatywna
    0.86
    BeginContext
    0.86
    fjspx
    0.85
    脚注の使い方
    0.82
     المعيارى
    0.80
    AxisAlignment
    0.77
     noDo
    0.77
    Act Density 0.018%

    No Known Activations