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

    Neuronpedia

    INDEX
    Explanations

    expressions of well-wishes and positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Certain
    -0.16
    ertain
    -0.15
    unt
    -0.15
    EO
    -0.15
    afari
    -0.14
    urch
    -0.14
    ór
    -0.14
    yl
    -0.14
     buck
    -0.14
    eca
    -0.14
    POSITIVE LOGITS
    nock
    0.17
    _Frame
    0.15
     оÑĤп
    0.15
    ouncer
    0.14
    cury
    0.14
    onte
    0.14
    ibri
    0.14
    uder
    0.14
    webdriver
    0.14
    оÑĨÑĸ
    0.14
    Act Density 0.029%

    No Known Activations