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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the significance, importance, and benefits of various aspects

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing significance or impact in relation to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idav
    -0.80
    plets
    -0.78
    pes
    -0.66
    MAP
    -0.65
    skirts
    -0.64
    adan
    -0.64
    etsk
    -0.64
    Downloadha
    -0.64
    Shut
    -0.64
    chel
    -0.63
    POSITIVE LOGITS
     magnitude
    1.15
     caliber
    1.09
     stature
    1.09
     calib
    1.05
     importance
    1.02
    course
    0.97
     utmost
    0.96
     size
    0.96
     proportions
    0.96
     renown
    0.94
    Act Density 0.325%

    No Known Activations