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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating alternative options or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    or more, less, older, larger, smaller, so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.52
    UserScript
    -0.50
    tanleria
    -0.50
     AttributeSet
    -0.48
    MLLoader
    -0.46
    ResponseWriter
    -0.44
     CreateTagHelper
    -0.44
    Lähteet
    -0.43
     Autorizaciones
    -0.42
    cristo
    -0.42
    POSITIVE LOGITS
     helft
    0.56
     moeite
    0.54
     inalámb
    0.52
     mijne
    0.52
    seamnă
    0.51
     or
    0.50
     equivalent
    0.49
     cantit
    0.49
     prieten
    0.48
     nák
    0.48
    Act Density 0.028%

    No Known Activations