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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions that emphasize precision and specificity

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

    phrases indicating precision or specificity

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

    precise, specific, and correct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <=",
    -0.95
     defaultstate
    -0.92
    TypedDataSet
    -0.90
    TagHelper
    -0.80
    Хьажоргаш
    -0.79
     snippetHide
    -0.78
    Personensuche
    -0.78
     '\\;'
    -0.77
    Portale
    -0.76
    bootstrapcdn
    -0.74
    POSITIVE LOGITS
     precise
    1.13
     correct
    1.06
     accurate
    1.06
     exact
    1.03
     Precise
    0.94
    precise
    0.89
    正確
    0.89
    correct
    0.87
    accurate
    0.86
     Accurate
    0.85
    Act Density 0.057%

    No Known Activations