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

    Neuronpedia

    INDEX
    Explanations

    first-person singular verbs ending in 'ed'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "I'd."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tension
    -0.63
     rigging
    -0.62
    zai
    -0.61
     Remem
    -0.60
     Tayyip
    -0.60
     momentum
    -0.60
     tensions
    -0.57
     Lambert
    -0.57
     constitu
    -0.57
     Sut
    -0.57
    POSITIVE LOGITS
    ividual
    1.39
    iversity
    1.10
    iamond
    1.02
    rew
    1.01
    ynamic
    0.94
    ynam
    0.93
    roid
    0.93
    istant
    0.92
    iverse
    0.92
    iscover
    0.90
    Act Density 0.024%

    No Known Activations