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

    Neuronpedia

    INDEX
    Explanations

    conditional statements involving exclusions or exceptions

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

    items after "except" or "but"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ÓW
    -0.38
    liceerd
    -0.37
    horabuena
    -0.35
    raits
    -0.34
     Daß
    -0.34
     Вікі
    -0.34
    行き
    -0.33
     endwhile
    -0.33
    PreferredItem
    -0.33
     comigo
    -0.33
    POSITIVE LOGITS
     except
    0.72
     excluding
    0.71
     Except
    0.68
    Except
    0.68
    except
    0.66
    exclude
    0.66
    excluding
    0.64
     excluded
    0.63
     excepting
    0.63
     excepted
    0.57
    Act Density 0.262%

    No Known Activations