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

    Neuronpedia

    INDEX
    Explanations

    phrases related to permissions and restrictions regarding usage rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    should not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     weihnachts
    -0.33
     cou
    -0.27
     ghế
    -0.26
     reaction
    -0.26
    ftagPool
    -0.26
     Paglinawan
    -0.25
     Furn
    -0.25
     ration
    -0.25
    ждествен
    -0.25
     dosis
    -0.24
    POSITIVE LOGITS
     Normdatei
    0.69
     kaarangay
    0.64
    matchCondition
    0.63
     חיצוניים
    0.61
    oredCriteria
    0.61
     ProtoMessage
    0.56
    eleste
    0.52
    fromnode
    0.52
     règlement
    0.52
    PostInfinity
    0.52
    Act Density 0.190%

    No Known Activations