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

    Neuronpedia

    INDEX
    Explanations

    references to quantity, quality, and appropriate measures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elves
    -0.15
    iddi
    -0.15
    hta
    -0.15
    eyen
    -0.15
    sburgh
    -0.14
    çĦ
    -0.14
     ê¼Ń
    -0.14
    ån
    -0.14
    ake
    -0.13
    ála
    -0.13
    POSITIVE LOGITS
     cave
    0.17
     caves
    0.17
    391
    0.16
    proper
    0.16
     cav
    0.15
     Proper
    0.15
     Masc
    0.15
     Misc
    0.14
     Morse
    0.14
    MainThread
    0.14
    Act Density 0.150%

    No Known Activations