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

    Neuronpedia

    INDEX
    Explanations

    pronouns 'they', 'their', and instances related to taking on a challenging or preparatory process

    oai_token-act-pair · gpt-3.5-turbo

    references to people or groups of people in general discussions or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CCC
    -0.64
    Offline
    -0.64
    gery
    -0.63
     Sequ
    -0.61
     Eleven
    -0.60
    amaz
    -0.59
    CLASSIFIED
    -0.59
    OTOS
    -0.58
     è£ıè¦ļéĨĴ
    -0.58
    Posts
    -0.57
    POSITIVE LOGITS
    're
    1.83
    've
    1.43
     are
    1.35
     themselves
    1.30
    'll
    1.25
     deserve
    1.21
     aren
    1.21
     perceive
    1.18
     were
    1.10
    'd
    1.06
    Act Density 0.227%

    No Known Activations