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

    Neuronpedia

    INDEX
    Explanations

    words related to causation and effects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verständlich
    -0.70
     Tatsache
    -0.68
    קישורים
    -0.68
     للمعارف
    -0.67
     EconPapers
    -0.65
    tagHelperRunner
    -0.64
    Datuak
    -0.64
     Administrativna
    -0.62
     surla
    -0.61
    Autoritní
    -0.61
    POSITIVE LOGITS
     CAUSE
    0.91
     Causes
    0.90
    causes
    0.90
     Caus
    0.84
     Cause
    0.82
     causes
    0.81
    Causes
    0.80
     havoc
    0.79
    caused
    0.78
     cause
    0.77
    Act Density 0.089%

    No Known Activations