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

    Neuronpedia

    INDEX
    Explanations

    country-related words and political or governmental references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    earchers
    -0.87
    utenberg
    -0.81
    aurus
    -0.80
    earch
    -0.77
    equality
    -0.76
    ories
    -0.76
    etting
    -0.76
    ilion
    -0.75
    ecause
    -0.75
    mith
    -0.73
    POSITIVE LOGITS
    hood
    1.28
     extraord
    0.97
    dom
    0.95
    doms
    0.94
    esses
    0.88
     who
    0.81
    gery
    0.78
    ess
    0.78
    ry
    0.77
    ishly
    0.75
    Act Density 1.528%

    No Known Activations