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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to attributes like simplicity, subtlety, and elegance

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and coordinating phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortmund
    -0.85
    ISE
    -0.80
    Ws
    -0.79
    SHIP
    -0.79
    olphins
    -0.77
    ciation
    -0.77
    ETS
    -0.77
    ESE
    -0.75
    æĥ
    -0.75
    ENCE
    -0.73
    POSITIVE LOGITS
     prone
    1.09
     therefore
    1.08
     adventurous
    1.05
     reliant
    1.02
     capable
    1.00
     unpredictable
    1.00
     responsive
    1.00
     flexible
    0.98
     efficient
    0.98
     focused
    0.97
    Act Density 0.193%

    No Known Activations