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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing the structure "As is **."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "is" followed by various descriptors or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iard
    -0.79
    istries
    -0.74
    glers
    -0.73
    ierce
    -0.69
     Puzzles
    -0.66
     pores
    -0.66
    blocks
    -0.65
    aukee
    -0.62
    ograms
    -0.62
    enh
    -0.61
    POSITIVE LOGITS
     customary
    1.33
     usual
    1.22
     evidenced
    1.14
     evident
    1.08
     typical
    0.95
     wont
    0.93
     tradition
    0.86
     common
    0.85
     standard
    0.85
     abundantly
    0.83
    Act Density 0.070%

    No Known Activations