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

    Neuronpedia

    INDEX
    Explanations

    phrases related to catching up with someone or something

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating interactions or connections with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.81
    ieri
    -0.79
    quer
    -0.75
    uld
    -0.75
    ray
    -0.71
    ouf
    -0.70
    amiya
    -0.69
    affected
    -0.68
    overe
    -0.68
    atically
    -0.66
    POSITIVE LOGITS
     regards
    0.91
     impunity
    0.90
     dignity
    0.90
     regard
    0.89
     Drill
    0.73
     Dragonbound
    0.71
     respect
    0.69
     girlfriends
    0.68
    erous
    0.66
     boredom
    0.65
    Act Density 0.064%

    No Known Activations