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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate inclusion or references to multiple elements or items

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

    Follows the word "including"

    np_acts-logits-general · gemini-2.0-flash

    listing specific instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.70
    Lähteet
    -0.70
     getItemId
    -0.69
    aksanaan
    -0.66
     humaines
    -0.66
     }}"></
    -0.63
     houſe
    -0.62
     silt
    -0.62
     Wilshire
    -0.61
    enterOuterAlt
    -0.60
    POSITIVE LOGITS
     those
    0.93
     including
    0.74
     the
    0.74
    INCLUDING
    0.74
     quelli
    0.70
     ostavi
    0.70
    including
    0.68
    TRIBUN
    0.66
     ones
    0.66
     its
    0.65
    Act Density 0.109%

    No Known Activations