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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "idd" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'id' or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.75
     metast
    -0.71
     Canaver
    -0.64
    TPP
    -0.63
    APH
    -0.62
     AUTHOR
    -0.62
    ãĥīãĥ©ãĤ´ãĥ³
    -0.60
    OPLE
    -0.59
     Prol
    -0.59
     tranqu
    -0.58
    POSITIVE LOGITS
    eenth
    1.01
    ski
    0.97
    olph
    0.94
    ety
    0.94
    itional
    0.93
    leground
    0.93
    lesh
    0.91
    olesc
    0.88
    elling
    0.88
    imensional
    0.86
    Act Density 0.011%

    No Known Activations