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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Saint" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sir
    -0.15
    uj
    -0.15
    ayne
    -0.15
    ัส
    -0.15
    aset
    -0.15
    vard
    -0.14
     Nov
    -0.14
    buie
    -0.14
     sticker
    -0.14
    Nov
    -0.14
    POSITIVE LOGITS
     Urb
    0.18
     Hipp
    0.17
     Hub
    0.17
    æ¨
    0.16
     Gilles
    0.16
     cloud
    0.16
     Andrews
    0.15
     Honor
    0.15
     Trojan
    0.15
     Frontier
    0.14
    Act Density 0.026%

    No Known Activations