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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elage
    -0.17
     Hugo
    -0.17
    triangle
    -0.15
    ugo
    -0.14
    terior
    -0.14
    amage
    -0.13
    stasy
    -0.13
     lore
    -0.13
     Hok
    -0.13
    atur
    -0.13
    POSITIVE LOGITS
     ÑĢÑĥ
    0.14
    andi
    0.14
    onde
    0.14
     بات
    0.14
    ovich
    0.14
    agal
    0.14
    qua
    0.14
    ernet
    0.13
    ector
    0.13
    leigh
    0.13
    Act Density 0.044%

    No Known Activations