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

    Neuronpedia

    INDEX
    Explanations

    mentions of modifications or alterations in policies or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loom
    -0.16
    essim
    -0.15
    edia
    -0.15
    è¡Ĩ
    -0.14
    monds
    -0.14
    æ°ĹãģĮ
    -0.14
     wed
    -0.14
    udd
    -0.14
     रà¤ĸ
    -0.14
    _imm
    -0.14
    POSITIVE LOGITS
    uren
    0.17
    ifetime
    0.16
    imers
    0.15
    æݪ
    0.15
    pad
    0.15
    ummies
    0.14
    £½
    0.14
    /add
    0.14
    eração
    0.14
    boxed
    0.13
    Act Density 0.057%

    No Known Activations