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

    Neuronpedia

    INDEX
    Explanations

    informal conversational expressions and phrases

    oai_token-act-pair · gpt-3.5-turbo

    informal expressions and commentary on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -1.09
    sequent
    -0.83
    ewitness
    -0.77
    sequently
    -0.73
    BuyableInstoreAndOnline
    -0.72
    qus
    -0.72
    oscopic
    -0.69
    ashington
    -0.68
    emporary
    -0.67
    erva
    -0.67
    POSITIVE LOGITS
     kinda
    1.43
     huh
    1.27
     pretty
    1.22
     dudes
    1.18
     stuff
    1.14
     crap
    1.13
     dude
    1.07
     freaking
    1.05
     yeah
    1.04
     REALLY
    1.03
    Act Density 1.318%

    No Known Activations