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

    Neuronpedia

    INDEX
    Explanations

    terms related to confirmation or validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rok
    -0.70
    Rok
    -0.70
     Ling
    -0.67
    z
    -0.61
     lingua
    -0.61
     Sk
    -0.58
    soever
    -0.58
    jsx
    -0.58
     kema
    -0.57
     house
    -0.55
    POSITIVE LOGITS
     Confirm
    2.66
     confirm
    2.63
     confirmed
    2.59
     confirmation
    2.52
     confirmations
    2.50
     confirms
    2.43
     Confirmed
    2.42
    confirmed
    2.38
     Confirmation
    2.38
     confirming
    2.37
    Act Density 0.085%

    No Known Activations