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

    Neuronpedia

    INDEX
    Explanations

    instances of direct speech or quotes within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     $_"
    -0.88
    躇
    -0.87
     Theſe
    -0.83
     Reſ
    -0.82
    期刊论文
    -0.80
     Efq
    -0.79
     greateſt
    -0.78
    tagHelperRunner
    -0.78
     iſt
    -0.77
     ſch
    -0.76
    POSITIVE LOGITS
    <eos>
    0.87
    ↵↵
    0.61
     The
    0.55
    The
    0.51
     chyb
    0.51
    .
    0.49
    "
    0.48
     "
    0.48
    gegangen
    0.47
    новременно
    0.47
    Act Density 0.101%

    No Known Activations