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

    Neuronpedia

    INDEX
    Explanations

    specific patterns and structures in programming code, particularly around syntax elements like brackets and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing braces and break statements in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    énario
    -0.32
    ClCompile
    -0.30
     Kong
    -0.27
     сем
    -0.26
    듬
    -0.26
    ModelAttribute
    -0.25
     œ
    -0.24
    œ
    -0.24
     Cong
    -0.24
    Bin
    -0.24
    POSITIVE LOGITS
     break
    3.06
    break
    2.88
     Break
    2.58
     breaks
    2.47
    Break
    2.36
     BREAK
    2.33
     breaking
    2.31
     broke
    2.19
     Breaks
    2.16
    BREAK
    2.09
    Act Density 0.265%

    No Known Activations