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

    Neuronpedia

    INDEX
    Explanations

    patterns and sequences of numeric values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     in
    -0.55
     last
    -0.51
    .
    -0.48
     just
    -0.45
     sólo
    -0.45
     really
    -0.44
    /
    -0.42
     paid
    -0.42
    マヨ
    -0.42
     first
    -0.41
    POSITIVE LOGITS
     BoxFit
    0.90
    ✨:
    0.87
     يتيمه
    0.87
     NSCoder
    0.86
     lenker
    0.80
    Datuak
    0.79
    abetes
    0.78
     Theſe
    0.78
     habet
    0.78
    '][]
    0.77
    Act Density 0.302%

    No Known Activations