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

    Neuronpedia

    INDEX
    Explanations

    names related to the keyword "Gh"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Gh."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    payer
    -0.86
    eers
    -0.78
    nings
    -0.76
    eering
    -0.74
     stewards
    -0.72
     Faust
    -0.70
    swick
    -0.69
    DOWN
    -0.66
    dated
    -0.65
     Proposition
    -0.64
    POSITIVE LOGITS
    ilst
    1.09
    ouls
    1.06
    oses
    0.96
    omes
    0.90
    adish
    0.90
    osh
    0.90
    amel
    0.90
    ulk
    0.89
    awar
    0.89
    ilit
    0.88
    Act Density 0.008%

    No Known Activations