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

    Neuronpedia

    INDEX
    Explanations

    punctuation, particularly dashes and parentheses, which are often used for emphasis or to provide additional information

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

    whether or if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.44
    EndContext
    -0.43
     owne
    -0.43
     eyeball
    -0.42
    цезда
    -0.41
    観音
    -0.40
     PeEnEo
    -0.40
    dized
    -0.40
     Seiz
    -0.40
    owner
    -0.39
    POSITIVE LOGITS
    Sklici
    0.55
     تانيه
    0.52
    principalTable
    0.47
    homonymie
    0.47
     Misalnya
    0.45
     conscientes
    0.44
     مرئيه
    0.44
    TagMode
    0.44
    matchCondition
    0.41
     tristes
    0.41
    Act Density 0.340%

    No Known Activations