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

    Neuronpedia

    INDEX
    Explanations

    phrases related to creation or production processes

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "making."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mub
    -0.76
     Vest
    -0.67
    ban
    -0.63
     scrimmage
    -0.60
    ombat
    -0.60
     vest
    -0.59
    ---------
    -0.58
    heter
    -0.57
     Suit
    -0.57
     Wick
    -0.56
    POSITIVE LOGITS
     sure
    0.90
    hift
    0.86
    ÄŁ
    0.85
    emort
    0.84
    itives
    0.81
    akable
    0.75
    awaru
    0.74
     merry
    0.72
    roid
    0.71
    Maker
    0.71
    Act Density 0.035%

    No Known Activations