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

    Neuronpedia

    INDEX
    Explanations

    references to rumors and their validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.80
    OpenHelper
    -0.55
    wegg
    -0.50
     Dames
    -0.48
    hitheater
    -0.48
     Expressway
    -0.48
     choice
    -0.47
    remadura
    -0.47
    creativecommons
    -0.46
    hskip
    -0.46
    POSITIVE LOGITS
     rumors
    1.41
     rumours
    1.37
     rumour
    1.36
     rumor
    1.33
     Rumors
    1.21
    Rumors
    1.13
     allegations
    1.06
     rumores
    1.06
     allegation
    1.02
     speculation
    1.00
    Act Density 0.252%

    No Known Activations