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

    Neuronpedia

    INDEX
    Explanations

    terms related to effort and performance

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

    Adverbs modifying adjectives

    np_acts-logits-general · gemini-2.0-flash

    intensifiers followed by adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Larger
    -1.09
     Larger
    -1.09
    Higher
    -1.08
     Longer
    -1.06
    Longer
    -1.04
     Faster
    -1.02
     Easier
    -1.02
     Smaller
    -1.02
    Smaller
    -1.00
    Bigger
    -1.00
    POSITIVE LOGITS
     very
    0.83
     extremely
    0.82
     super
    0.79
     incredibly
    0.78
     really
    0.75
     unbelievably
    0.71
     exceptionally
    0.71
     extraordinarily
    0.66
     exceedingly
    0.64
     thật
    0.64
    Act Density 0.423%

    No Known Activations