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

    Neuronpedia

    INDEX
    Explanations

    statements emphasizing the concept of everything being significant or noteworthy in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     altogether
    -0.17
    PyObject
    -0.15
     others
    -0.14
    uddle
    -0.14
     Lamar
    -0.14
    ynn
    -0.13
    ette
    -0.13
    yr
    -0.13
    ongyang
    -0.13
     m
    -0.13
    POSITIVE LOGITS
    False
    0.15
    ikel
    0.15
    chn
    0.15
    antino
    0.15
    erdale
    0.14
    CCI
    0.14
    _except
    0.14
    illisecond
    0.14
    목
    0.14
    lings
    0.14
    Act Density 0.061%

    No Known Activations