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

    Neuronpedia

    INDEX
    Explanations

    phrases or commands starting with "Enter"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Enter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    killer
    -0.66
     conviction
    -0.66
    76561
    -0.65
     backdrop
    -0.65
     gunned
    -0.64
     laundering
    -0.62
     coun
    -0.61
    killing
    -0.61
    acca
    -0.60
     goodwill
    -0.60
    POSITIVE LOGITS
    prise
    1.54
    prises
    1.50
    tainment
    1.35
    prising
    1.34
    tain
    1.26
    taining
    1.21
    TAIN
    0.90
    tained
    0.87
    tis
    0.87
    ipher
    0.81
    Act Density 0.011%

    No Known Activations