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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĿĪ
    -0.17
    çģµ
    -0.17
    acha
    -0.17
    ENDOR
    -0.15
    igit
    -0.14
    ubits
    -0.14
    hur
    -0.14
     Coord
    -0.13
    Fab
    -0.13
    лаж
    -0.13
    POSITIVE LOGITS
    antis
    0.16
    556
    0.15
    çķª
    0.15
    опол
    0.14
    etz
    0.14
    _lng
    0.14
     нез
    0.14
    rek
    0.14
     radius
    0.14
    radius
    0.13
    Act Density 0.001%

    No Known Activations