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

    Neuronpedia

    INDEX
    Explanations

    critiques or evaluations in a written text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial implications and policy proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lovely
    -0.61
     denotes
    -0.60
     FANTASY
    -0.59
     Nanto
    -0.58
     Drama
    -0.57
     aston
    -0.57
     Sung
    -0.57
     biography
    -0.56
     splendid
    -0.56
     brill
    -0.56
    POSITIVE LOGITS
     federally
    0.89
     regulatory
    0.81
     environmentally
    0.78
     costly
    0.72
     unregulated
    0.71
     statewide
    0.71
    competitive
    0.71
     lucrative
    0.70
     discriminatory
    0.69
     legisl
    0.69
    Act Density 1.887%

    No Known Activations