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

    Neuronpedia

    INDEX
    Explanations

    references to hacking activities and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opers
    -0.17
    ousse
    -0.16
    inka
    -0.15
    ãĥĥãĥĦ
    -0.15
    bid
    -0.15
    olt
    -0.14
    RIES
    -0.14
    edeki
    -0.14
    IEWS
    -0.14
    ping
    -0.14
    POSITIVE LOGITS
    ney
    0.32
    tiv
    0.31
    athon
    0.30
    intosh
    0.28
    NEY
    0.27
    neys
    0.19
    paces
    0.19
    eo
    0.18
    ncy
    0.18
    ebe
    0.18
    Act Density 0.008%

    No Known Activations