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

    Neuronpedia

    INDEX
    Explanations

    attributes related to parentheses and punctuation usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uro
    -0.14
    ắng
    -0.14
    forward
    -0.14
    à¤ľà¤¬
    -0.14
     draft
    -0.13
    .uc
    -0.13
    indsight
    -0.13
    ông
    -0.13
    424
    -0.13
    icer
    -0.13
    POSITIVE LOGITS
    /ion
    0.15
    utely
    0.14
    @Web
    0.14
    uala
    0.14
     dikke
    0.14
    алÑĥ
    0.14
    crets
    0.13
    aN
    0.13
     Setter
    0.13
    íĥķ
    0.13
    Act Density 0.005%

    No Known Activations