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

    Neuronpedia

    INDEX
    Explanations

    braces and structure indicating the end of code blocks

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

    closing braces and whitespace/indentation in code structure.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.63
     للمعارف
    -0.51
    ⤹
    -0.49
     TextAppearance
    -0.46
     lenker
    -0.45
     مرئيه
    -0.42
     dostaw
    -0.39
    SharedCtor
    -0.38
    ByVersion
    -0.38
    insegna
    -0.38
    POSITIVE LOGITS
     catch
    0.89
    catch
    0.80
     Catch
    0.69
     else
    0.69
    Catch
    0.62
     catches
    0.60
    else
    0.59
     finally
    0.58
     catching
    0.56
    CATCH
    0.55
    Act Density 0.232%

    No Known Activations