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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to exclusivity or singularity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "sole" in various contexts indicating exclusivity or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caf
    -0.68
     horm
    -0.67
     Machines
    -0.66
     Drugs
    -0.64
     Everywhere
    -0.64
    enegger
    -0.64
    hops
    -0.63
     Kids
    -0.63
     Eggs
    -0.63
     Cards
    -0.61
    POSITIVE LOGITS
     propriet
    1.26
     occupant
    0.94
     superpower
    0.93
     purpose
    0.91
    ieth
    0.91
     exception
    0.89
    mn
    0.88
    eenth
    0.86
     sole
    0.83
     survivor
    0.83
    Act Density 0.031%

    No Known Activations