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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to classifications or naming conventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ossa
    -0.15
    anken
    -0.15
    indre
    -0.15
    idle
    -0.14
    vably
    -0.13
    lasses
    -0.13
    lesc
    -0.13
    æ©Ł
    -0.13
     XCT
    -0.13
    357
    -0.13
    POSITIVE LOGITS
     hol
    0.16
    adu
    0.15
    kea
    0.15
     ho
    0.15
    -Sah
    0.15
     Hol
    0.14
    صÙĩ
    0.14
     Spir
    0.14
    aley
    0.14
    edula
    0.14
    Act Density 0.004%

    No Known Activations