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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" followed by a certain context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inx
    -0.75
    ulner
    -0.74
    quished
    -0.60
    inders
    -0.60
    eners
    -0.60
    ricanes
    -0.57
    icons
    -0.57
    listed
    -0.57
     Pwr
    -0.56
    yip
    -0.56
    POSITIVE LOGITS
     regard
    1.66
     vein
    1.39
     case
    1.29
     circumstance
    1.28
     respect
    1.27
     manner
    1.23
     context
    1.22
     respects
    1.21
     regards
    1.20
     instance
    1.19
    Act Density 0.082%

    No Known Activations