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

    Neuronpedia

    INDEX
    Explanations

    phrases related to concepts or definitions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibble
    -0.76
    hari
    -0.74
     indications
    -0.74
    items
    -0.70
    wcsstore
    -0.67
    river
    -0.66
    furt
    -0.65
    Reports
    -0.65
     batches
    -0.65
    medium
    -0.64
    POSITIVE LOGITS
     unmarried
    0.70
     behold
    0.69
    ËĪ
    0.69
     wield
    0.69
     die
    0.68
     inhabit
    0.64
     live
    0.64
    ils
    0.64
     spiritually
    0.63
     overcome
    0.63
    Act Density 0.095%

    No Known Activations