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

    Neuronpedia

    INDEX
    Explanations

    the word "not" preceding another verb

    oai_token-act-pair · gpt-3.5-turbo

    negative assertions or denials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pric
    -0.71
    lined
    -0.68
     Cutter
    -0.66
     Tow
    -0.65
     Eisen
    -0.64
     Gone
    -0.63
     yeah
    -0.63
     Canaveral
    -0.63
    GGGGGGGG
    -0.62
    itiz
    -0.62
    POSITIVE LOGITS
     intend
    1.18
     hesitate
    1.12
     belong
    1.08
     reside
    1.07
     exist
    1.05
     condone
    1.04
     specify
    1.03
     necessarily
    1.03
     discriminate
    1.02
     approve
    1.00
    Act Density 0.100%

    No Known Activations