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

    Neuronpedia

    INDEX
    Explanations

    references to tangible or physical entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to materialism or physical substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enda
    -0.65
    ULTS
    -0.62
    unct
    -0.62
    cffffcc
    -0.61
    FLAG
    -0.61
    ecake
    -0.60
     Pis
    -0.59
    GBT
    -0.58
     Beard
    -0.57
     Strauss
    -0.57
    POSITIVE LOGITS
    ized
    1.13
    ity
    1.12
    izes
    1.07
    istic
    1.07
    ization
    1.04
    izing
    1.03
    ize
    1.03
    ised
    0.99
    isations
    0.98
    izations
    0.95
    Act Density 0.040%

    No Known Activations