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

    Neuronpedia

    INDEX
    Explanations

    instances of specific legal terms and formal declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stanovnika
    -0.88
     createState
    -0.87
    原始内容存档于
    -0.84
    createCanvas
    -0.80
     lenker
    -0.80
    oredCriteria
    -0.79
    CodedInputStream
    -0.79
     ligiloj
    -0.79
     Jody
    -0.79
     Freuden
    -0.79
    POSITIVE LOGITS
    [toxicity=0]
    1.71
     }^{*}$
    0.88
    帖最后由
    0.80
    /}
    0.77
     {*}
    0.73
    assertArray
    0.72
     .=
    0.68
    ்கள்
    0.68
     $*$
    0.68
    *)
    0.67
    Act Density 0.003%

    No Known Activations