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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "un" suggesting negation or reversal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yat
    -0.18
    allis
    -0.15
    ýš
    -0.14
    umb
    -0.14
    orny
    -0.14
    onu
    -0.14
     pen
    -0.14
    ument
    -0.13
    ALLY
    -0.13
    zl
    -0.13
    POSITIVE LOGITS
     Uns
    0.15
    ãĥ¯ãĥ¼
    0.15
    reation
    0.14
    .Modules
    0.14
    _VERBOSE
    0.14
    à¹īà¸Ń
    0.14
    esco
    0.14
    (coder
    0.14
     Creed
    0.14
    Toolkit
    0.13
    Act Density 0.002%

    No Known Activations