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

    Neuronpedia

    INDEX
    Explanations

    phrases related to philosophical concepts and critical thinking

    oai_token-act-pair · gpt-3.5-turbo

    sentences that assert conclusions or summarizations in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     convoy
    -0.88
     neighb
    -0.87
     landfall
    -0.84
     pocket
    -0.82
    ributes
    -0.82
     costing
    -0.80
     shelling
    -0.80
     purse
    -0.76
     trave
    -0.76
     warr
    -0.75
    POSITIVE LOGITS
     Suppose
    1.54
     Thus
    1.45
     Hence
    1.43
     Indeed
    1.37
     Whereas
    1.36
     Consequently
    1.34
    Thus
    1.32
     Accordingly
    1.30
     Certainly
    1.25
     Moreover
    1.25
    Act Density 0.404%

    No Known Activations