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

    Neuronpedia

    INDEX
    Explanations

    questions and statements involving inquiries or requests for information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Демографія
    -0.87
     imidlertid
    -0.74
     >=",
    -0.73
     useAppContext
    -0.72
     entanto
    -0.69
     infatti
    -0.69
    however
    -0.68
     however
    -0.68
     tuttavia
    -0.68
    lunda
    -0.66
    POSITIVE LOGITS
     afterwards
    0.72
     Then
    0.71
    Then
    0.69
     afterward
    0.67
     потом
    0.65
     thereafter
    0.65
     sitten
    0.64
     danach
    0.63
     then
    0.62
     later
    0.61
    Act Density 0.577%

    No Known Activations