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

    Neuronpedia

    INDEX
    Explanations

    intentions or goals expressed through the word "aim."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.17
     unto
    -0.17
    uous
    -0.15
    ctic
    -0.15
    aire
    -0.15
    ff
    -0.15
    mits
    -0.14
    esa
    -0.14
    oma
    -0.14
    asio
    -0.14
    POSITIVE LOGITS
    lessly
    0.31
    fully
    0.19
    LESS
    0.18
    higher
    0.17
    QUARE
    0.16
    547
    0.16
    unda
    0.16
    ÑĤеÑģÑĮ
    0.15
    prov
    0.15
    sharp
    0.15
    Act Density 0.014%

    No Known Activations