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

    Neuronpedia

    INDEX
    Explanations

    words related to discussions or issues being talked about

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardo
    -0.74
    olyn
    -0.71
    ramid
    -0.70
    ignt
    -0.70
    omp
    -0.67
    inyl
    -0.65
    oÄŁ
    -0.64
    Dim
    -0.63
     Yates
    -0.63
    ATES
    -0.62
    POSITIVE LOGITS
    matter
    1.08
     topics
    1.03
     topic
    0.93
     discussed
    0.86
     debated
    0.84
     matter
    0.83
     discussion
    0.81
     Topics
    0.81
    ussed
    0.79
    ivities
    0.79
    Act Density 0.068%

    No Known Activations