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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles preceded by the '@' symbol

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media handles or usernames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emonium
    -0.77
     aspir
    -0.68
     wrapped
    -0.67
     wrap
    -0.67
     elect
    -0.66
     assum
    -0.66
     concentrate
    -0.65
     envelop
    -0.65
     exorc
    -0.65
     remake
    -0.64
    POSITIVE LOGITS
    realDonaldTrump
    1.41
    #$
    1.38
    @@@@@@@@
    1.04
    gmail
    1.01
    wik
    0.99
    GS
    0.87
    abc
    0.87
    NO
    0.86
    GOP
    0.86
    NC
    0.85
    Act Density 0.018%

    No Known Activations