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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing collective experiences and observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nish
    -0.17
    clip
    -0.15
    ìĦ±
    -0.14
    leston
    -0.14
    ãģ»ãģĨ
    -0.14
    alg
    -0.14
    ulg
    -0.14
    ernals
    -0.14
    lags
    -0.13
    aille
    -0.13
    POSITIVE LOGITS
    Ñĩа
    0.17
    istra
    0.16
    ÑĢави
    0.15
    itters
    0.15
    çe
    0.14
    istrovstvÃŃ
    0.14
    ucken
    0.14
     Yard
    0.14
    elden
    0.14
    ande
    0.14
    Act Density 0.052%

    No Known Activations