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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ongoing changes or trends, particularly in product popularity and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucu
    -0.18
    EMPLARY
    -0.17
    Æ¡
    -0.16
    ajo
    -0.16
    roker
    -0.15
    'gc
    -0.14
    ect
    -0.14
    nement
    -0.14
    .gdx
    -0.13
    pai
    -0.13
    POSITIVE LOGITS
    straint
    0.17
    quot
    0.15
     regard
    0.15
    ominator
    0.14
    ige
    0.14
    olang
    0.14
    .Merge
    0.14
    /↵↵↵↵
    0.14
    ĨĴ
    0.14
    ABS
    0.13
    Act Density 0.060%

    No Known Activations