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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word 'up'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disson
    -0.71
    ¯¯¯¯
    -0.66
     overwhel
    -0.64
    ³³³³³³³³³³³³³³³³
    -0.64
     cath
    -0.64
     hect
    -0.63
    ¯¯¯¯¯¯¯¯
    -0.63
     mileage
    -0.61
    ________________________
    -0.61
     cac
    -0.61
    POSITIVE LOGITS
    dates
    1.52
    olicy
    1.26
    grades
    1.15
    graded
    1.13
    stairs
    1.12
    dating
    1.11
    edia
    1.07
    etsk
    1.02
    rison
    1.01
    etts
    0.98
    Act Density 0.024%

    No Known Activations