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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to governance or political systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     XNUMX
    -1.08
    NUMX
    -0.99
    ̵
    -0.80
    +#+#
    -0.79
     ​​
    -0.79
     continúas
    -0.79
     .;
    -0.78
     GenerationType
    -0.76
    ⁇
    -0.74
    👈
    -0.74
    POSITIVE LOGITS
     everybody
    0.73
    Everybody
    0.72
     Everybody
    0.71
     Though
    0.71
    Whilst
    0.71
    Though
    0.70
    ѝ
    0.68
     somebody
    0.67
     Whilst
    0.65
     escoger
    0.64
    Act Density 4.102%

    No Known Activations