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

    Neuronpedia

    INDEX
    Explanations

    quantities and measurements related to weight and volume

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utra
    -0.15
     dne
    -0.15
    abor
    -0.14
    aty
    -0.14
     References
    -0.14
     convin
    -0.14
    лива
    -0.14
     du
    -0.14
    combe
    -0.14
    agine
    -0.13
    POSITIVE LOGITS
    átka
    0.17
    meer
    0.16
    stractions
    0.14
    alon
    0.14
    ãĥ¼ãĥ«ãĥī
    0.14
    quez
    0.13
    inox
    0.13
    onsense
    0.13
     altogether
    0.13
    etter
    0.13
    Act Density 0.025%

    No Known Activations