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

    Neuronpedia

    INDEX
    Explanations

    specific word pairs

    oai_token-act-pair · gpt-3.5-turbo

    references to groups, teams, or comparisons involving multiple entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uggest
    -0.67
     therap
    -0.62
     explan
    -0.62
    conserv
    -0.61
    ogle
    -0.59
     assum
    -0.59
    informed
    -0.59
     destro
    -0.58
    isphere
    -0.56
    opian
    -0.56
    POSITIVE LOGITS
     Yon
    0.72
     Balt
    0.70
     Les
    0.68
     Lie
    0.68
    BuyableInstoreAndOnline
    0.67
     Yorkshire
    0.67
     Leeds
    0.66
     Lv
    0.66
     Burk
    0.65
     USS
    0.64
    Act Density 0.452%

    No Known Activations