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

    Neuronpedia

    INDEX
    Explanations

    information related to historical events, political controversies, and cultural references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dragonbound
    -0.72
    ogy
    -0.70
     Opportun
    -0.69
    antha
    -0.65
    hower
    -0.63
     gorilla
    -0.61
     Syl
    -0.60
    ãĥ¼ãĥĨ
    -0.59
    achus
    -0.58
    ipation
    -0.58
    POSITIVE LOGITS
    11
    1.06
    09
    1.03
    16
    1.02
    22
    1.02
    02
    1.01
    12
    1.01
    13
    1.01
    10
    1.01
    31
    0.99
    08
    0.99
    Act Density 0.336%

    No Known Activations