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

    Neuronpedia

    INDEX
    Explanations

    phrases and statistics related to educational achievements and institutional practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arda
    -0.16
    ayar
    -0.16
    asser
    -0.15
    antan
    -0.15
    arrass
    -0.15
    ↵↵
    -0.14
    jal
    -0.14
     "'
    -0.14
    orz
    -0.14
     Garland
    -0.14
    POSITIVE LOGITS
     Luo
    0.21
     Kenya
    0.20
     hence
    0.20
     Ken
    0.19
    ---↵
    0.18
     keen
    0.17
    Ken
    0.17
     Uganda
    0.17
     dint
    0.16
     Chim
    0.16
    Act Density 0.674%

    No Known Activations