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

    Neuronpedia

    INDEX
    Explanations

    phrases related to justifications and defenses for actions

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

    excuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rizona
    -0.46
    diğimiz
    -0.41
     Cataloging
    -0.39
     relação
    -0.39
     Wikimedijinoj
    -0.38
    отно
    -0.37
    impres
    -0.37
    meiras
    -0.37
    hages
    -0.36
    idios
    -0.36
    POSITIVE LOGITS
    enderror
    0.47
    HttpPut
    0.47
     excuse
    0.46
     excused
    0.43
    Inflater
    0.43
    Portale
    0.42
     BoxFit
    0.41
    excuse
    0.41
    izoen
    0.41
    TargetApi
    0.40
    Act Density 0.047%

    No Known Activations