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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific name or term "Gh."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Gh" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.81
    nings
    -0.79
    eering
    -0.77
     stewards
    -0.72
    manship
    -0.69
     Stra
    -0.65
    payer
    -0.65
    going
    -0.64
    DOWN
    -0.63
    swick
    -0.63
    POSITIVE LOGITS
    ouls
    1.21
    ilst
    1.12
    oses
    1.11
    oul
    1.02
    omes
    0.98
    ilit
    0.97
    addafi
    0.96
    adish
    0.93
    ulk
    0.93
    azi
    0.92
    Act Density 0.019%

    No Known Activations