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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     imobili
    -0.41
    Dimanche
    -0.40
     estadounidenses
    -0.40
     työn
    -0.40
     indispensables
    -0.38
     Venise
    -0.38
     civilización
    -0.38
    Annexes
    -0.38
    writeFileSync
    -0.38
     brillantes
    -0.38
    POSITIVE LOGITS
     MH
    0.72
    Rptr
    0.68
     uncertainties
    0.65
     snippetHide
    0.65
     uncertain
    0.64
     PH
    0.63
     uncertainty
    0.63
    posedge
    0.63
    MH
    0.62
    WH
    0.61
    Act Density 0.316%

    No Known Activations