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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating spatial or temporal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bidden
    -0.15
    oretical
    -0.15
    quires
    -0.14
    quel
    -0.14
    ARIANT
    -0.14
    ãĤĵãģª
    -0.14
    (crate
    -0.14
    oeff
    -0.14
    ODE
    -0.14
    Äįan
    -0.14
    POSITIVE LOGITS
     advantage
    0.20
    linkplain
    0.17
     cabo
    0.17
    ause
    0.16
     detriment
    0.16
     fondo
    0.16
     tune
    0.16
     contrario
    0.15
    abe
    0.15
     дело
    0.15
    Act Density 0.777%

    No Known Activations