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

    Neuronpedia

    INDEX
    Explanations

    references to lists or catalog entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dent
    -0.18
    zem
    -0.17
    endo
    -0.15
    enstein
    -0.15
    pest
    -0.15
    idor
    -0.15
    iland
    -0.14
    dff
    -0.14
    ifa
    -0.14
    ollen
    -0.14
    POSITIVE LOGITS
    ade
    0.45
    ad
    0.31
    ADE
    0.25
    rade
    0.24
    ades
    0.23
    ад
    0.22
    ande
    0.20
    ada
    0.20
     ade
    0.20
    aded
    0.19
    Act Density 0.011%

    No Known Activations