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

    Neuronpedia

    INDEX
    Explanations

    nested parentheses and brackets in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sexes
    -0.73
    tagHelper
    -0.73
     snippetHide
    -0.72
    ՚
    -0.72
    principalColumn
    -0.71
    MethodManager
    -0.71
    AxisAlignment
    -0.70
    "):
    -0.69
    mybatisplus
    -0.69
     Efq
    -0.69
    POSITIVE LOGITS
     Италијани
    0.52
    ьаж
    0.49
    庁
    0.45
     special
    0.45
    /
    0.45
     (
    0.43
    Controllo
    0.43
    кисло
    0.43
    īg
    0.43
    bangan
    0.43
    Act Density 0.369%

    No Known Activations