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

    Neuronpedia

    INDEX
    Explanations

    references to support and resources for individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģķãģĦ
    -0.18
    imler
    -0.15
    Ether
    -0.15
     há»
    -0.15
    oples
    -0.15
    UTERS
    -0.14
     Exists
    -0.14
    ozor
    -0.14
    /*č↵
    -0.14
    ERM
    -0.14
    POSITIVE LOGITS
     ne
    0.40
     ned
    0.30
     Ne
    0.29
    _ne
    0.26
    -ne
    0.26
     dire
    0.25
     n
    0.25
     NE
    0.23
     badly
    0.23
     require
    0.23
    Act Density 0.181%

    No Known Activations