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

    Neuronpedia

    INDEX
    Explanations

    references to legal actions or decisions regarding individuals and their status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poichè
    -0.88
     således
    -0.78
     endast
    -0.73
    几人
    -0.73
     ainfi
    -0.72
    깥
    -0.72
     אך
    -0.70
     yalnızca
    -0.68
     feroit
    -0.68
     آنان
    -0.67
    POSITIVE LOGITS
     really
    1.07
     somebody
    1.06
     sort
    1.06
     kind
    1.03
     basically
    0.98
     gonna
    0.97
     everybody
    0.97
     yeah
    0.93
     maybe
    0.93
    somebody
    0.93
    Act Density 1.477%

    No Known Activations