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

    Neuronpedia

    INDEX
    Explanations

    the name "Fran" within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ch"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.64
     Soy
    -0.62
     corrid
    -0.61
    ERC
    -0.59
     unexplained
    -0.58
    GMT
    -0.58
     monarch
    -0.58
    TEXTURE
    -0.57
     ejac
    -0.57
     Xin
    -0.56
    POSITIVE LOGITS
    icago
    1.31
    ambers
    1.13
    icken
    1.08
    ocolate
    1.06
    inese
    1.04
    amps
    1.03
    itect
    1.01
    ampions
    1.01
    andise
    1.00
    amber
    0.99
    Act Density 0.048%

    No Known Activations