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

    Neuronpedia

    INDEX
    Explanations

    concepts related to fairness and public policy implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endeavour
    -0.17
    owards
    -0.17
     Whilst
    -0.16
    Additionally
    -0.16
     whilst
    -0.16
    lei
    -0.16
     Additionally
    -0.15
     initialise
    -0.15
     advancements
    -0.15
     detriment
    -0.15
    POSITIVE LOGITS
     precisely
    0.20
     precinct
    0.16
     Qaeda
    0.15
     (=
    0.14
     pronto
    0.14
     roughly
    0.14
    #ad
    0.14
     regime
    0.14
     hence
    0.13
     ((((
    0.13
    Act Density 1.131%

    No Known Activations