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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or qualifiers that introduce uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.67
    WriteTagHelper
    -0.60
    出版年
    -0.55
     Nowak
    -0.55
    RenderAtEndOf
    -0.55
    Fw
    -0.54
    ogia
    -0.54
     Tut
    -0.51
     Flour
    -0.50
    bonucleic
    -0.50
    POSITIVE LOGITS
    albeit
    0.94
     albeit
    0.89
    beit
    0.78
    Kaieteur
    0.71
     admittedly
    0.65
     minOccurs
    0.64
    yelidikan
    0.63
     somewhat
    0.63
    Hopefully
    0.62
     ostavi
    0.62
    Act Density 0.150%

    No Known Activations