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

    Neuronpedia

    INDEX
    Explanations

    connections between causative phrases and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     незавершена
    -0.63
     يتيمه
    -0.56
     otomatig
    -0.53
     للاسماء
    -0.51
     فريبيس
    -0.50
    isContained
    -0.48
     Audiodateien
    -0.48
     useAppContext
    -0.45
     Plenty
    -0.44
     McCar
    -0.44
    POSITIVE LOGITS
     finally
    0.72
     ultimately
    0.67
     lastly
    0.63
     respectively
    0.61
     moreover
    0.60
     indeed
    0.60
     finalmente
    0.59
     successively
    0.59
    finally
    0.58
     firstly
    0.57
    Act Density 1.281%

    No Known Activations