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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     in
    -0.53
     for
    -0.51
    set
    -0.48
    pro
    -0.45
     دیکھیے
    -0.45
     to
    -0.45
    Personendaten
    -0.44
    组
    -0.44
    util
    -0.44
     the
    -0.43
    POSITIVE LOGITS
     tartalomajánló
    1.00
     betweenstory
    0.94
     ujednoznacz
    0.91
    TagMode
    0.86
     TextInputType
    0.85
     AssemblyCulture
    0.82
     FontWeight
    0.79
    esgue
    0.78
    \{\\
    0.78
    HtmlAttribute
    0.78
    Act Density 0.619%

    No Known Activations