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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating location or presence of things in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udence
    -0.67
     Mania
    -0.61
    Buyable
    -0.61
     mortality
    -0.59
     Development
    -0.59
    è¦ļéĨĴ
    -0.58
     Loss
    -0.58
     appre
    -0.58
     Transformation
    -0.57
    imize
    -0.57
    POSITIVE LOGITS
    abad
    0.76
    女
    0.75
     Nieto
    0.73
    asin
    0.71
    nesday
    0.71
    swick
    0.68
     dots
    0.65
    ffield
    0.65
     Zar
    0.64
    urai
    0.64
    Act Density 0.137%

    No Known Activations