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

    Neuronpedia

    INDEX
    Explanations

    ordinal terms and related rankings in a sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Convention
    -0.18
    ãģ£ãģı
    -0.17
    eck
    -0.16
    ãĥ£
    -0.15
     halde
    -0.15
     Exped
    -0.15
    گز
    -0.14
    ãģıãĤī
    -0.14
     lua
    -0.14
     Tro
    -0.14
    POSITIVE LOGITS
    -round
    0.23
     round
    0.23
     leg
    0.18
    leg
    0.17
    -leg
    0.16
    round
    0.15
     meeting
    0.15
     Leg
    0.15
    -string
    0.15
    ourn
    0.15
    Act Density 0.048%

    No Known Activations