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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Pass" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Passover holiday

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.75
    ä¸ī
    -0.73
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
     Kut
    -0.62
     stressed
    -0.60
     narrator
    -0.59
     extent
    -0.59
     GEAR
    -0.59
     headed
    -0.56
    IRD
    -0.55
    POSITIVE LOGITS
    engers
    1.39
     Pass
    1.24
    Pass
    1.16
    words
    1.11
    es
    1.09
    aic
    1.02
    enger
    1.01
     Passing
    0.98
    pass
    0.95
    wd
    0.90
    Act Density 0.005%

    No Known Activations