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

    Neuronpedia

    INDEX
    Explanations

    common occurrences or activities

    oai_token-act-pair · gpt-3.5-turbo

    recurring phrases that highlight frequency or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.81
    plates
    -0.73
    gae
    -0.71
    agate
    -0.69
    oops
    -0.69
    ENE
    -0.68
    abad
    -0.67
    gur
    -0.65
    VR
    -0.65
     Showdown
    -0.65
    POSITIVE LOGITS
    entimes
    1.50
     overlooked
    1.07
    theless
    1.01
     resorted
    0.92
     touted
    0.90
     encountered
    0.90
     misunderstood
    0.89
     referred
    0.88
     cited
    0.87
     times
    0.86
    Act Density 0.034%

    No Known Activations