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

    Neuronpedia

    INDEX
    Explanations

    phrases that express limitation or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ync
    -0.17
     Imported
    -0.16
    ardy
    -0.16
    GS
    -0.15
    ryn
    -0.14
    æĺŃ
    -0.14
    ied
    -0.14
    ิà¸ķร
    -0.14
     PS
    -0.14
    IED
    -0.14
    POSITIVE LOGITS
    ordion
    0.15
    ultipart
    0.15
     mặt
    0.14
    eking
    0.14
    ãģĮãģĦ
    0.14
     BST
    0.13
    .Undef
    0.13
     Bölgesi
    0.13
    angelog
    0.13
    uras
    0.13
    Act Density 0.000%

    No Known Activations