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

    Neuronpedia

    INDEX
    Explanations

    specific adjectives and nouns that describe conditions or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Houſe
    -0.67
     Ceux
    -0.66
     houſe
    -0.64
     namelijk
    -0.63
     Italij
    -0.63
     doubtnut
    -0.63
     nemlig
    -0.62
     mør
    -0.62
     võimal
    -0.61
     näm
    -0.61
    POSITIVE LOGITS
    <bos>
    2.00
    '
    0.99
    ’
    0.99
     فريبيس
    0.71
    المشاركات
    0.71
    brainly
    0.70
    хьтан
    0.66
    '%(
    0.61
    '||
    0.58
    милия
    0.56
    Act Density 10.497%

    No Known Activations