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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts indicating unnecessary elements or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adel
    -0.16
    terr
    -0.15
    quel
    -0.15
    pheric
    -0.15
    utenberg
    -0.14
    ноÑģÑĤ
    -0.14
    otton
    -0.14
    вÑĸд
    -0.14
     yr
    -0.14
    illery
    -0.13
    POSITIVE LOGITS
    .Apis
    0.18
    æĬŀ
    0.15
     Redistributions
    0.14
     åı·
    0.14
    PickerController
    0.14
    ëĭ¹
    0.14
    GRES
    0.14
    alous
    0.13
     punishable
    0.13
    777
    0.13
    Act Density 0.011%

    No Known Activations