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

    Neuronpedia

    INDEX
    Explanations

    web URLs containing specific keywords

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "we."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gratification
    -0.70
     contradictions
    -0.67
    ional
    -0.65
     conflicts
    -0.61
     contradiction
    -0.60
     quo
    -0.60
     derail
    -0.59
     rug
    -0.58
     sucker
    -0.58
     LSD
    -0.58
    POSITIVE LOGITS
    bsite
    1.43
    eping
    1.27
    aving
    1.18
    aning
    1.17
    athered
    1.14
    lder
    1.13
    igh
    1.10
    avers
    1.10
    akens
    1.10
    akening
    1.09
    Act Density 0.084%

    No Known Activations