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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating sequences or actions that are connected or linked

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     otherwise
    -0.15
     Kaplan
    -0.15
     way
    -0.14
     risk
    -0.14
     enough
    -0.14
    kte
    -0.14
    -0.13
     coz
    -0.13
    ago
    -0.13
     WAY
    -0.13
    POSITIVE LOGITS
     Sez
    0.16
    δή
    0.15
    llen
    0.15
    IOException
    0.15
    resa
    0.14
    à¸Ĺะ
    0.14
    нÑİ
    0.14
    ีà¸ģ
    0.14
    InputBorder
    0.14
    ãĥªãĤ¢
    0.14
    Act Density 0.006%

    No Known Activations