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

    Neuronpedia

    INDEX
    Explanations

    first names containing "rus"

    oai_token-act-pair · gpt-3.5-turbo

    references to Russian-related terms or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     testament
    -0.69
     fet
    -0.65
     magnitude
    -0.64
    ĻĤ
    -0.63
     lesson
    -0.62
    phies
    -0.62
    ARK
    -0.61
     stakes
    -0.61
    ells
    -0.61
     fidelity
    -0.60
    POSITIVE LOGITS
    rus
    1.05
    hea
    0.87
    ç·
    0.84
    hes
    0.83
    ãĥ´ãĤ¡
    0.79
    hip
    0.77
    é¾įåĸļ士
    0.77
    hess
    0.77
    he
    0.76
     Vaugh
    0.76
    Act Density 0.010%

    No Known Activations