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

    Neuronpedia

    INDEX
    Explanations

    XML or HTML-like syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seven
    -0.18
    ä¸ĥ
    -0.17
    Seven
    -0.17
    ypi
    -0.16
    ernes
    -0.16
     hay
    -0.16
     ä¸ĥ
    -0.15
     seven
    -0.15
    irected
    -0.15
     nim
    -0.15
    POSITIVE LOGITS
    0.39
    0.22
    329
    0.21
                  ↵
    0.20
    411
    0.19
    421
    0.19
    339
    0.19
    341
    0.18
    381
    0.18
    --------------
    0.17
    Act Density 0.020%

    No Known Activations