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

    Neuronpedia

    INDEX
    Explanations

    ending curly braces in code or text structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lam
    -0.15
    etter
    -0.15
    etto
    -0.14
    èĬĻ
    -0.14
    plx
    -0.14
    utter
    -0.14
    zych
    -0.14
    ients
    -0.13
    ord
    -0.13
    \Bridge
    -0.13
    POSITIVE LOGITS
    ↵↵↵↵↵↵
    0.18
    ↵↵↵↵↵
    0.17
    ↵↵↵↵↵↵↵
    0.17
     Emerging
    0.16
    ↵↵↵↵↵↵↵↵↵↵
    0.15
    ↵↵↵↵↵↵↵↵
    0.15
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.15
    apur
    0.15
     addCriterion
    0.15
    abaj
    0.14
    Act Density 0.030%

    No Known Activations