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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to governance and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alla
    -0.16
    illes
    -0.16
    mate
    -0.15
    ãģĭãģ«
    -0.15
    alue
    -0.15
    uddy
    -0.14
    agt
    -0.14
    enek
    -0.14
    opp
    -0.14
    arken
    -0.14
    POSITIVE LOGITS
     whom
    0.40
     who
    0.33
     ones
    0.29
     whose
    0.28
     denen
    0.27
     those
    0.27
     them
    0.25
    who
    0.25
     kteÅĻÃŃ
    0.24
    whose
    0.24
    Act Density 0.380%

    No Known Activations