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

    Neuronpedia

    INDEX
    Explanations

    numbers or related information such as times, dates, and points in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    channelAvailability
    -0.51
     DRAG
    -0.50
    Sad
    -0.49
    HCR
    -0.48
    Package
    -0.45
    BTC
    -0.45
    ILA
    -0.44
     Haram
    -0.43
    aido
    -0.43
    incinn
    -0.43
    POSITIVE LOGITS
    eways
    0.57
    eway
    0.56
    ety
    0.55
    eely
    0.52
    forth
    0.52
     intervening
    0.49
    else
    0.48
    adas
    0.47
    enegger
    0.46
     versa
    0.45
    Act Density 0.710%

    No Known Activations