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

    Neuronpedia

    INDEX
    Explanations

    verbal phrases related to significant changes or eliminations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the reduction or elimination of regulations and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.91
    spot
    -0.69
    si
    -0.67
    Sym
    -0.64
    oof
    -0.64
    Streamer
    -0.63
    told
    -0.63
     wearer
    -0.61
     belongs
    -0.61
     attest
    -0.61
    POSITIVE LOGITS
     abolish
    0.80
     taxes
    0.75
     deport
    0.74
     tariffs
    0.73
     discretionary
    0.73
     pensions
    0.73
     unnecessary
    0.72
     wasteful
    0.72
     abol
    0.72
     legislative
    0.71
    Act Density 0.231%

    No Known Activations