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

    Neuronpedia

    INDEX
    Explanations

    references to manuscripts and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wald
    -0.16
    oti
    -0.16
    aldo
    -0.16
    eczy
    -0.15
    ÅĻeh
    -0.14
    æĢĢ
    -0.14
    illard
    -0.14
    oni
    -0.14
    emony
    -0.13
    otypes
    -0.13
    POSITIVE LOGITS
    eller
    0.18
    ellar
    0.17
    δεÏĤ
    0.16
    oppable
    0.16
     Tas
    0.15
    ellers
    0.15
    ariat
    0.15
    665
    0.15
    imonial
    0.15
    matic
    0.14
    Act Density 0.017%

    No Known Activations