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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or political processes

    oai_token-act-pair · gpt-3.5-turbo

    topics related to financial or economic distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frenchman
    -0.58
     Cadillac
    -0.57
    bart
    -0.56
    ¬¼
    -0.55
    00200000
    -0.55
    ãĤ¹ãĥĪ
    -0.54
    ahon
    -0.51
    ãĥ´
    -0.50
    Chicken
    -0.50
    °
    -0.49
    POSITIVE LOGITS
     themselves
    1.01
     apiece
    1.01
     or
    0.95
     respectively
    0.88
    their
    0.83
     equivalents
    0.82
     whereas
    0.81
     similar
    0.80
    +.
    0.78
     (>
    0.78
    Act Density 0.575%

    No Known Activations