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

    Neuronpedia

    INDEX
    Explanations

    references to passwords and credentials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oser
    -0.15
    upy
    -0.15
    .toolbox
    -0.14
    utters
    -0.14
    anche
    -0.14
    zy
    -0.14
    hem
    -0.14
    izia
    -0.13
    gsub
    -0.13
    iesta
    -0.13
    POSITIVE LOGITS
    aily
    0.16
    rin
    0.14
    mare
    0.13
    Fail
    0.13
     su
    0.13
     comp
    0.13
    aken
    0.13
    ARS
    0.13
    castle
    0.13
    æŃ
    0.13
    Act Density 0.013%

    No Known Activations