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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dependency and reliability

    oai_token-act-pair · gpt-3.5-turbo

    words related to dependence and reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mehran
    -0.79
    Ĥª
    -0.77
     Noon
    -0.69
    ulton
    -0.67
     Jury
    -0.63
     Milan
    -0.63
     Zurich
    -0.62
     Trial
    -0.62
    wagen
    -0.61
     Helsinki
    -0.61
    POSITIVE LOGITS
    ency
    1.10
    encies
    1.05
    enza
    0.98
    ents
    0.97
    ancies
    0.97
    encia
    0.92
    uously
    0.88
    ancy
    0.88
    entle
    0.86
    iable
    0.86
    Act Density 0.016%

    No Known Activations