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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "subject"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific topic or subject within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERROR
    -0.76
    olyn
    -0.69
    hetto
    -0.68
    ATES
    -0.68
    ces
    -0.66
    IELD
    -0.64
    omp
    -0.64
    AUD
    -0.63
    GBT
    -0.62
    aukee
    -0.61
    POSITIVE LOGITS
    matter
    1.33
    ivity
    1.28
    ivist
    1.16
    ivities
    1.16
    ively
    1.09
    ivism
    1.08
     matter
    1.07
     Matter
    1.00
    ion
    0.98
    ivation
    0.95
    Act Density 0.020%

    No Known Activations