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

    Neuronpedia

    INDEX
    Explanations

    names and titles of political leaders or government officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.68
     Herodotus
    -0.53
    yaf
    -0.50
    zam
    -0.50
    Stateless
    -0.49
    BagConstraints
    -0.49
    atoday
    -0.48
    κρα
    -0.46
    zerland
    -0.45
     Organisator
    -0.45
    POSITIVE LOGITS
     Prime
    1.34
     prime
    1.23
    Prime
    1.22
     PM
    1.03
    prime
    1.02
     PRIME
    1.02
    PRIME
    0.97
     premi
    0.90
     premiers
    0.88
     Perdana
    0.86
    Act Density 0.240%

    No Known Activations