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

    Neuronpedia

    INDEX
    Explanations

    words related to authenticity or exclusivity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to authenticity, domestication, exclusivity, and skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tongue
    -0.73
     resemblance
    -0.68
     descriptor
    -0.67
     penetration
    -0.67
     deception
    -0.65
     attendant
    -0.64
     penet
    -0.60
     sway
    -0.60
     fingers
    -0.59
     vain
    -0.59
    POSITIVE LOGITS
    ication
    1.75
    icated
    1.68
    icating
    1.64
    ics
    1.56
    ically
    1.55
    ications
    1.55
    icism
    1.55
    icate
    1.53
    icative
    1.50
    icator
    1.48
    Act Density 0.106%

    No Known Activations