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

    Neuronpedia

    INDEX
    Explanations

    exclamatory statements and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (*(
    -0.16
    åı¦
    -0.15
    gnore
    -0.15
    cheid
    -0.15
    ĥĿ
    -0.15
    ValuePair
    -0.14
    åı¦ä¸Ģ
    -0.14
    ãģ¯ãģļ
    -0.14
    ίν
    -0.14
    ék
    -0.14
    POSITIVE LOGITS
    1
    0.53
    ï¼ij
    0.35
    01
    0.35
    Û±
    0.32
    âijł
    0.30
    âĤģ
    0.24
    १
    0.23
    001
    0.21
     firstly
    0.20
    à¹ij
    0.19
    Act Density 0.104%

    No Known Activations