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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment or criticism towards certain topics or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .unlink
    -0.16
    ãĥ¼ãĤ¿ãĥ¼
    -0.15
    ฤ
    -0.14
    à¸ī
    -0.14
    ÑģÑĤав
    -0.14
    }}],↵
    -0.14
    ãĤ¯ãĥĪ
    -0.14
    amu
    -0.14
     Bail
    -0.14
    deen
    -0.13
    POSITIVE LOGITS
    zw
    0.17
    adero
    0.16
    ussen
    0.15
    íľ´
    0.15
     Mos
    0.15
    ynch
    0.14
    );$
    0.14
    *sizeof
    0.14
    ana
    0.14
    ä¸Ģèµ·
    0.14
    Act Density 0.007%

    No Known Activations