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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "more" and related phrases indicating an increase or continuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    पन
    -0.15
    rastructure
    -0.15
    кÑĥваннÑı
    -0.15
    aklı
    -0.14
     uncomment
    -0.14
    iggins
    -0.14
    icro
    -0.14
    æĴ®
    -0.14
     conting
    -0.14
    qui
    -0.14
    POSITIVE LOGITS
    areth
    0.15
     McM
    0.14
    inkel
    0.14
    lech
    0.14
    au
    0.14
    izm
    0.13
    rella
    0.13
     JC
    0.13
    illon
    0.13
    726
    0.13
    Act Density 0.018%

    No Known Activations