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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries regarding beliefs and their foundations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     بيها
    -0.77
     مشين
    -0.66
    日閲覧
    -0.50
    lapsingToolbar
    -0.48
     probably
    -0.47
     nowhere
    -0.46
    ]();
    -0.46
     nemlig
    -0.45
    Сылтамалар
    -0.45
     Baillargeon
    -0.44
    POSITIVE LOGITS
    ?
    1.35
    ?”
    1.34
    ?"
    1.30
    ?
    1.28
    ?</
    1.25
    ?}
    1.21
    ?''
    1.20
    ?'
    1.20
    ?")
    1.19
    ?’
    1.17
    Act Density 0.674%

    No Known Activations