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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to performance and optimization

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

    preceding adverbs of degree

    np_acts-logits-general · gemini-2.0-flash

    noticeably affect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.75
     Efq
    -0.71
    🏻‍♀️
    -0.69
     saites
    -0.69
    TintMode
    -0.69
     itſelf
    -0.67
     ſtate
    -0.67
     nakalista
    -0.67
     poffe
    -0.66
    iprot
    -0.66
    POSITIVE LOGITS
     noticeable
    0.72
     increased
    0.58
     compensated
    0.57
    AddTagHelper
    0.57
     increases
    0.56
     compensate
    0.56
     avantage
    0.56
    Theore
    0.55
     increase
    0.55
     max
    0.54
    Act Density 0.592%

    No Known Activations