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

    Neuronpedia

    INDEX
    Explanations

    the word "info" and statistics related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mente
    -0.24
    /or
    -0.20
    ร
    -0.20
    hood
    -0.19
    hips
    -0.19
    nt
    -0.19
    hip
    -0.19
    ized
    -0.19
    aire
    -0.18
    evin
    -0.18
    POSITIVE LOGITS
    otr
    0.20
    ëģĶ
    0.20
    éro
    0.19
    ãģ¾ãģŁ
    0.19
    ä¹Ī
    0.18
    uation
    0.17
    ot
    0.17
    istory
    0.17
    sumer
    0.17
    imized
    0.17
    Act Density 0.386%

    No Known Activations