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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dynamic actions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.27
     snippetHide
    -1.27
     ſtate
    -1.27
     faſt
    -1.20
     ſever
    -1.19
     purpoſe
    -1.18
     ویکی‌پدیا
    -1.17
     pleaſure
    -1.16
     Reſ
    -1.15
     juſ
    -1.15
    POSITIVE LOGITS
     
    0.93
    ,
    0.73
    .
    0.69
    ↵↵
    0.67
    </h2>
    0.67
     The
    0.66
     "
    0.66
    -
    0.61
     “
    0.60
     A
    0.60
    Act Density 5.043%

    No Known Activations