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

    Neuronpedia

    INDEX
    Explanations

    terms related to evidence and substantial contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ạp
    -0.15
     âĸ³
    -0.15
    chine
    -0.15
    vis
    -0.14
    EDIA
    -0.14
    croft
    -0.14
    ingo
    -0.14
    chw
    -0.13
    зÑĮ
    -0.13
    chie
    -0.13
    POSITIVE LOGITS
     Lack
    0.17
     oneself
    0.15
    exion
    0.15
    unch
    0.15
    rå
    0.15
     Variable
    0.15
    ella
    0.14
     manner
    0.14
    [NUM
    0.14
    rame
    0.14
    Act Density 0.007%

    No Known Activations