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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to negation and exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bills
    -0.15
    uci
    -0.15
     تÙĩ
    -0.15
    GO
    -0.14
    kee
    -0.14
    ianne
    -0.14
    indr
    -0.14
    ule
    -0.14
    uez
    -0.13
    ReuseIdentifier
    -0.13
    POSITIVE LOGITS
    urtles
    0.16
    Appear
    0.16
    vault
    0.15
    ÑĢеÑħ
    0.15
    ostel
    0.14
    WXYZ
    0.14
    è¨Ģãģ£ãģŁ
    0.14
    ãĥ¯ãĤ¤ãĥĪ
    0.14
    격
    0.14
    orte
    0.14
    Act Density 0.001%

    No Known Activations