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

    Neuronpedia

    INDEX
    Explanations

    programmatic structure and control flow elements within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -1.31
     
    -1.12
    . 
    -0.78
     
    -0.69
    ".
    -0.64
     AssemblyCulture
    -0.63
     
    -0.61
    -0.61
     
    -0.59
    ⁠
    -0.59
    POSITIVE LOGITS
    ↵↵↵
    0.78
    ↵↵↵↵
    0.70
    noinspection
    0.70
    ↵↵↵↵↵
    0.66
    ↵↵↵↵↵↵↵
    0.65
    ↵↵↵↵↵↵
    0.63
    ↵↵↵↵↵↵↵↵
    0.59
    ↵↵↵↵↵↵↵↵↵
    0.58
    >--}}
    0.55
    ↵↵↵↵↵↵↵↵↵↵
    0.53
    Act Density 0.040%

    No Known Activations