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

    Neuronpedia

    INDEX
    Explanations

    references to official meetings and discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     dicono
    -0.54
     brille
    -0.52
     ANCHE
    -0.49
     ananas
    -0.49
     lepid
    -0.48
     prouve
    -0.48
    Ephe
    -0.48
     vogli
    -0.48
     diable
    -0.48
     nomme
    -0.47
    POSITIVE LOGITS
     meeting
    1.27
     meetings
    1.21
    meeting
    1.20
     Meeting
    1.19
    Meeting
    1.17
     Meetings
    1.11
    meetings
    1.10
     MEETING
    1.04
    Meetings
    1.04
     meet
    0.84
    Act Density 0.076%

    No Known Activations