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

    Neuronpedia

    INDEX
    Explanations

    the word "Sol" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sol" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shapeshifter
    -0.76
    è¦ļéĨĴ
    -0.69
    intosh
    -0.64
    REE
    -0.63
    SHIP
    -0.63
     special
    -0.63
     Ancients
    -0.63
    IRD
    -0.61
    reader
    -0.60
     seniors
    -0.60
    POSITIVE LOGITS
    ving
    1.09
    stice
    1.09
    itary
    1.09
    omon
    1.06
    ved
    1.04
    vable
    1.04
    oshenko
    0.97
    itaire
    0.96
    ange
    0.93
    itic
    0.91
    Act Density 0.017%

    No Known Activations