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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms, particularly those related to organizational structures or educational settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -operator
    -0.15
    UCE
    -0.15
    umps
    -0.15
    yms
    -0.15
    _nd
    -0.15
    levation
    -0.14
    eyi
    -0.14
    luk
    -0.14
    agen
    -0.14
    atile
    -0.14
    POSITIVE LOGITS
    etri
    0.16
    973
    0.15
     rejo
    0.14
    ãģĦãģĭ
    0.14
    cke
    0.13
     Vanity
    0.13
    æĬľ
    0.13
    etin
    0.13
    Destroyed
    0.13
     Expl
    0.13
    Act Density 0.033%

    No Known Activations