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

    Neuronpedia

    INDEX
    Explanations

    references to demographic groups and the actions or conditions affecting them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hopkins
    -0.15
    ãĥ£
    -0.15
    lád
    -0.14
    /umd
    -0.14
    ãĥ©ãĥ³
    -0.14
     ngoại
    -0.14
    ukes
    -0.14
    ahat
    -0.14
    raj
    -0.14
    alty
    -0.13
    POSITIVE LOGITS
    液
    0.16
    orsch
    0.15
    imdi
    0.15
    CLU
    0.14
    isms
    0.13
    곡
    0.13
    nick
    0.13
    loc
    0.13
    à¸ĺรรม
    0.13
    ãĥ³ãĥĸ
    0.13
    Act Density 0.004%

    No Known Activations