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

    Neuronpedia

    INDEX
    Explanations

    actions and decisions related to planning and teaching

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osemite
    -0.15
    -many
    -0.14
    ucker
    -0.14
    almost
    -0.14
    uars
    -0.13
    okud
    -0.13
    пи
    -0.13
    ylland
    -0.13
    olec
    -0.13
    uchen
    -0.13
    POSITIVE LOGITS
     some
    0.82
    some
    0.66
     Some
    0.62
    Some
    0.58
    ä¸ĢäºĽ
    0.55
     SOME
    0.54
    _some
    0.51
    .some
    0.50
     qualche
    0.48
     einige
    0.47
    Act Density 0.593%

    No Known Activations