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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives that indicate levels of effectiveness or performance

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

    Comes before comparative adjectives

    np_acts-logits-general · gemini-2.0-flash

    degrees of intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.68
    出版年
    -0.54
    MessageOf
    -0.53
    msgTypes
    -0.50
    EndContext
    -0.50
    ंदीखरीदारी
    -0.48
    intios
    -0.48
     يتيمه
    -0.47
     himſelf
    -0.46
     DbType
    -0.46
    POSITIVE LOGITS
     ändå
    0.48
     invokingState
    0.45
     Autres
    0.41
     prestaciones
    0.39
     Inscrivez
    0.38
     yoktur
    0.38
     femininos
    0.37
     suprême
    0.37
    достатки
    0.36
     Völker
    0.36
    Act Density 0.892%

    No Known Activations