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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions related to amounts or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adh
    -0.16
    ramer
    -0.14
    adius
    -0.14
    urrency
    -0.14
    ette
    -0.13
    iss
    -0.13
    sm
    -0.13
    æ®
    -0.13
    inh
    -0.13
    stuff
    -0.13
    POSITIVE LOGITS
     times
    0.19
    áÄį
    0.17
     different
    0.16
     consecutive
    0.16
     layers
    0.15
     hours
    0.14
     syll
    0.14
    VERSION
    0.14
     beers
    0.14
     people
    0.14
    Act Density 0.304%

    No Known Activations