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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving underlining or highlighting of variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jsdelivr
    -0.62
     form
    -0.62
     orec
    -0.62
     Dempsey
    -0.60
     apparence
    -0.59
    Hrsg
    -0.58
    पाद
    -0.58
    iph
    -0.58
     bez
    -0.58
     Mog
    -0.57
    POSITIVE LOGITS
    underline
    1.53
    TintMode
    0.96
    ImageContext
    0.96
     Underlying
    0.93
     underlined
    0.89
    noted
    0.86
    thâu
    0.84
     underline
    0.83
     AspNetCore
    0.80
     noted
    0.79
    Act Density 0.129%

    No Known Activations