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

    Neuronpedia

    INDEX
    Explanations

    references to power dynamics and authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NavController
    -0.46
     universality
    -0.45
     UNIVERSAL
    -0.42
    CION
    -0.40
     endTime
    -0.40
    rimid
    -0.40
    PWD
    -0.40
     setTime
    -0.40
     Universal
    -0.39
     nakalista
    -0.39
    POSITIVE LOGITS
    цездатний
    0.51
    antMatchers
    0.48
    Tembelea
    0.46
     temper
    0.44
     cultivation
    0.43
    tagext
    0.42
     cultivated
    0.41
    jores
    0.40
    mergeFrom
    0.40
     étudi
    0.39
    Act Density 0.084%

    No Known Activations