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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific phrases mentioning obtaining items or information

    oai_token-act-pair · gpt-3.5-turbo

    opportunities and offers related to content availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.58
    itored
    -0.57
    ornings
    -0.56
     exacerbated
    -0.55
     bolstered
    -0.54
    xtap
    -0.53
     overwhel
    -0.53
     strengthened
    -0.51
    phasis
    -0.49
     deterrent
    -0.49
    POSITIVE LOGITS
     ______
    0.61
     pokemon
    0.61
     Unicode
    0.59
    Pokémon
    0.59
     Pokémon
    0.58
     english
    0.58
     Xiaomi
    0.58
     crochet
    0.58
     awesome
    0.57
     Anime
    0.57
    Act Density 1.246%

    No Known Activations