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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "one"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    нина
    -0.16
    avers
    -0.15
    ListOf
    -0.15
    ä¸ĢåĪĩ
    -0.15
    kest
    -0.15
    lac
    -0.14
    оÑĢоÑĤ
    -0.14
    eking
    -0.14
    CDATA
    -0.14
    annis
    -0.13
    POSITIVE LOGITS
     if
    0.29
     among
    0.24
     fo
    0.24
     them
    0.24
    /all
    0.21
    åħ¶ä¸Ń
    0.21
     none
    0.20
    	if
    0.18
     из
    0.18
     If
    0.18
    Act Density 0.108%

    No Known Activations