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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tatsache
    -0.81
    קישורים
    -0.80
     للمعارف
    -0.73
     strå
    -0.68
     Betts
    -0.67
    paddingVertical
    -0.66
     Fl
    -0.66
    Ema
    -0.65
     Haller
    -0.65
     mellitus
    -0.65
    POSITIVE LOGITS
     CAUSE
    1.44
     Caus
    1.42
     cause
    1.42
     Causes
    1.41
     Cause
    1.41
    causes
    1.37
     causes
    1.36
     caused
    1.26
    caused
    1.26
    cause
    1.26
    Act Density 0.102%

    No Known Activations