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

    Neuronpedia

    INDEX
    Explanations

    statements or questions that require verification or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rok
    -0.73
    z
    -0.71
     Rok
    -0.71
     Sk
    -0.70
    tas
    -0.63
    Tas
    -0.62
     Pan
    -0.62
     lingua
    -0.61
    Sk
    -0.60
     yat
    -0.60
    POSITIVE LOGITS
     confirmations
    1.53
     Confirm
    1.48
     Confirmation
    1.39
     confirms
    1.33
     Confirmed
    1.33
     confirmation
    1.30
     confirm
    1.29
    CONFIRM
    1.29
     confirmed
    1.29
     Affirm
    1.27
    Act Density 0.127%

    No Known Activations