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

    Neuronpedia

    INDEX
    Explanations

    numerical data representing research results or statistical findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.48
     Đường
    -0.37
    viewDid
    -0.36
     незавершена
    -0.34
    égi
    -0.34
     GenerationType
    -0.33
     bedo
    -0.33
     sixth
    -0.32
    WireFormatLite
    -0.32
    ברס
    -0.32
    POSITIVE LOGITS
    出版年
    0.68
    :✨
    0.65
     Roskov
    0.57
    9
    0.57
    ########.
    0.55
    IUrlHelper
    0.52
    ViewFeatures
    0.49
     صوتيه
    0.48
    parsedMessage
    0.47
     שוליים
    0.45
    Act Density 0.383%

    No Known Activations