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

    Neuronpedia

    INDEX
    Explanations

    imperative verbs

    oai_token-act-pair · gpt-3.5-turbo

    common verbs and phrases related to communication and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pron
    -0.74
    eli
    -0.72
    beat
    -0.69
    grad
    -0.67
    quart
    -0.66
    pac
    -0.64
    agen
    -0.64
    verified
    -0.62
    enei
    -0.62
    packing
    -0.61
    POSITIVE LOGITS
     theirs
    1.33
     hers
    1.18
     something
    1.15
     them
    1.14
     anything
    1.07
     yours
    1.04
     everything
    1.03
     ours
    0.97
     mine
    0.90
     another
    0.90
    Act Density 0.415%

    No Known Activations