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

    Neuronpedia

    INDEX
    Explanations

    key actions, states, or descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingham
    -0.15
    ailing
    -0.15
    ylland
    -0.14
    sons
    -0.14
    ãĥ£
    -0.14
    ñas
    -0.14
    ainment
    -0.14
    leftright
    -0.14
    ieux
    -0.14
    tk
    -0.14
    POSITIVE LOGITS
    ione
    0.15
    thalm
    0.14
    adio
    0.14
    æĦıæĢĿ
    0.14
    lica
    0.14
    kili
    0.14
     Herz
    0.14
     Chall
    0.14
    odie
    0.14
     Wes
    0.14
    Act Density 0.002%

    No Known Activations