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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and social regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to participation in unlawful activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Farage
    -0.59
     Medals
    -0.59
     Ankara
    -0.57
     Ans
    -0.55
    Cruz
    -0.55
     Cree
    -0.54
    Uk
    -0.53
     Tehran
    -0.53
    UFC
    -0.51
     Senegal
    -0.50
    POSITIVE LOGITS
     depends
    0.84
    pires
    0.83
     involves
    0.81
     constitutes
    0.79
     requires
    0.78
     consists
    0.76
     varies
    0.75
     entails
    0.72
     occurs
    0.71
     refers
    0.69
    Act Density 0.748%

    No Known Activations