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

    Neuronpedia

    INDEX
    Explanations

    terms related to units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to econometrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cloth
    -0.67
    selection
    -0.65
    uctor
    -0.63
    pmwiki
    -0.63
     reserve
    -0.61
    caps
    -0.61
    stocks
    -0.59
    boss
    -0.58
     loving
    -0.58
    critical
    -0.57
    POSITIVE LOGITS
    allic
    1.18
    imet
    1.05
    rics
    1.03
    rium
    1.00
    abolic
    0.97
    rial
    0.96
    eor
    0.95
    reon
    0.90
    abol
    0.90
     Ping
    0.84
    Act Density 0.019%

    No Known Activations