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

    Neuronpedia

    INDEX
    Explanations

    negative prefixes or negations indicating a lack or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asje
    -0.15
    lamaz
    -0.15
    agnostic
    -0.15
    /***/
    -0.15
    ÏĢή
    -0.14
    extras
    -0.14
    .partial
    -0.14
     numberWith
    -0.14
    	Copyright
    -0.13
    'gc
    -0.13
    POSITIVE LOGITS
    min
    0.18
     min
    0.15
    oji
    0.15
    ling
    0.15
     traditional
    0.14
    ori
    0.14
    nen
    0.14
     necessarily
    0.14
     Quint
    0.14
    ities
    0.14
    Act Density 0.089%

    No Known Activations