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

    Neuronpedia

    INDEX
    Explanations

    the presence of the character "Ã" and its variations in the text

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

    accented characters from non-English languages.

    oai_token-act-pair · gemini-1.5-proTriggered by @nrbln

    French accented characters, particularly "é" and "à".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @nrbln

    special characters or placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithMany
    -0.51
     BoxDecoration
    -0.40
     abzu
    -0.34
    inaison
    -0.33
    inhabited
    -0.32
    Verkehr
    -0.32
    енча
    -0.32
     při
    -0.32
    npmjs
    -0.32
    brauch
    -0.32
    POSITIVE LOGITS
    
    0.67
     Winaray
    0.57
     �
    0.56
    nables
    0.54
     errno
    0.51
    grafa
    0.50
    ftime
    0.50
     CURIAM
    0.49
     Taktlose
    0.49
     nonUne
    0.48
    Act Density 0.002%

    No Known Activations