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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "is" occurring in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "is"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wills
    -0.71
     encounters
    -0.68
     Ministers
    -0.64
     Want
    -0.63
     wishes
    -0.63
     seats
    -0.63
     floats
    -0.63
     Commun
    -0.63
    urches
    -0.62
     Malf
    -0.62
    POSITIVE LOGITS
    rael
    1.33
    olation
    1.10
    nt
    1.02
    senal
    0.99
    cussion
    0.97
    olate
    0.97
    olated
    0.95
    omorphic
    0.95
    ometric
    0.95
    othermal
    0.91
    Act Density 0.501%

    No Known Activations