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

    Neuronpedia

    INDEX
    Explanations

    terms related to high points or maximum levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mk
    -0.16
    isco
    -0.15
    EST
    -0.15
    se
    -0.15
     Pais
    -0.15
    est
    -0.15
    rena
    -0.14
    ISCO
    -0.14
    iral
    -0.14
    ÄĻż
    -0.14
    POSITIVE LOGITS
    achu
    0.19
    uliar
    0.19
    ered
    0.18
    stery
    0.17
    istrovstvÃŃ
    0.17
    erc
    0.16
    #ab
    0.15
    stagram
    0.15
    675
    0.15
     RoundedRectangle
    0.15
    Act Density 0.015%

    No Known Activations