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

    Neuronpedia

    INDEX
    Explanations

    nouns and attributes associated with capability and achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maj
    -0.15
    ighthouse
    -0.15
    unan
    -0.15
    enos
    -0.14
    åĪ°åºķ
    -0.14
    ãĥīãĥ«
    -0.14
     ajust
    -0.14
    jsc
    -0.14
    hdl
    -0.14
    ãĥ¼ãĤ¸
    -0.13
    POSITIVE LOGITS
     Tou
    0.15
    rets
    0.15
    arend
    0.15
    inq
    0.14
    cef
    0.14
    墨
    0.14
     Kling
    0.14
    ahi
    0.14
    elter
    0.13
    .§
    0.13
    Act Density 0.001%

    No Known Activations