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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or a collective reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifa
    -0.15
    czy
    -0.14
    ,SIGNAL
    -0.14
    nin
    -0.14
    ÙĪاء
    -0.14
    eler
    -0.13
    ì§Ī
    -0.13
    hee
    -0.13
    nám
    -0.13
    ÄIJT
    -0.13
    POSITIVE LOGITS
    isque
    0.17
     коÑĤоÑĢого
    0.14
     which
    0.14
    ÙĪدÙĩ
    0.14
    ãĥ¥
    0.14
    aina
    0.13
    oret
    0.13
    ologically
    0.13
     Topic
    0.13
     коÑĤоÑĢ
    0.13
    Act Density 0.414%

    No Known Activations