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

    Neuronpedia

    INDEX
    Explanations

    technical terms and jargon related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ه
    -0.98
    zelfde
    -0.93
    ی
    -0.90
    y
    -0.81
    ה
    -0.75
    ي
    -0.74
    י
    -0.69
    ി
    -0.68
    ி
    -0.68
    يًا
    -0.64
    POSITIVE LOGITS
    <bos>
    1.62
    JKLM
    0.67
    ſelves
    0.65
    juries
    0.64
    %;">
    0.60
    🤣🤣
    0.60
    nologies
    0.59
    pośred
    0.57
     purpoſe
    0.57
    penis
    0.56
    Act Density 5.888%

    No Known Activations