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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to academic or scholarly content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.23
    a
    -0.21
    oles
    -0.20
    edException
    -0.19
    e
    -0.18
    aes
    -0.18
    esine
    -0.18
    edb
    -0.18
    or
    -0.18
    edes
    -0.18
    POSITIVE LOGITS
    ting
    0.25
    linger
    0.19
    sum
    0.18
     juste
    0.17
    tings
    0.16
    ross
    0.15
    rosse
    0.15
    adia
    0.15
    uš
    0.15
    itle
    0.15
    Act Density 0.065%

    No Known Activations