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

    Neuronpedia

    INDEX
    Explanations

    instances of the "bos" token, indicating the start of a significant section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.62
    Архівовано
    -0.51
     /\.
    -0.51
    tagHelper
    -0.51
    SBATCH
    -0.50
    ?,?,
    -0.49
     Ta
    -0.47
     >=",
    -0.47
    TagHelpers
    -0.45
     устраи
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.81
     itſelf
    0.76
    MessageTagHelper
    0.73
     myſelf
    0.73
     iſt
    0.72
     ſtand
    0.72
    !';
    0.70
     faſt
    0.69
     pleaſure
    0.69
    /**
    0.69
    Act Density 0.052%

    No Known Activations