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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eteria
    -0.17
    ufen
    -0.17
    ä¼ij
    -0.16
    ÐIJÑĢÑħÑĸв
    -0.16
    okol
    -0.15
    ">//
    -0.15
    arent
    -0.14
    ullo
    -0.14
     wound
    -0.14
    quential
    -0.13
    POSITIVE LOGITS
    agher
    0.15
    zin
    0.15
    adows
    0.14
    ormal
    0.14
    pras
    0.14
    alı
    0.14
    zelf
    0.14
    èĥĮ
    0.14
    ario
    0.14
     Apollo
    0.14
    Act Density 0.021%

    No Known Activations