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

    Neuronpedia

    INDEX
    Explanations

    questions or inquiries about information seeking and determining understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     I
    -0.51
     Cap
    -0.49
    Discussion
    -0.47
    toko
    -0.47
    さんも
    -0.47
    anese
    -0.46
     Hughes
    -0.45
    нні
    -0.45
     F
    -0.45
    也被
    -0.45
    POSITIVE LOGITS
     how
    1.58
     whether
    1.40
     cuáles
    1.17
    whether
    1.14
    berapa
    1.12
     cómo
    1.09
    how
    1.09
     why
    1.09
     what
    1.08
     WHETHER
    1.06
    Act Density 0.402%

    No Known Activations