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

    Neuronpedia

    INDEX
    Explanations

    terms indicating superiority or ranking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orida
    -0.15
    aliz
    -0.15
    rsa
    -0.15
    rech
    -0.15
    æº
    -0.14
    chsel
    -0.14
    ieties
    -0.14
    elo
    -0.14
    ürn
    -0.14
    ipi
    -0.14
    POSITIVE LOGITS
    EGIN
    0.16
     ticking
    0.14
    ols
    0.14
    ÏĢοι
    0.14
     kettle
    0.14
     Grape
    0.14
    orte
    0.13
     Ju
    0.13
    ims
    0.13
     tick
    0.13
    Act Density 0.007%

    No Known Activations