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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to testing and assessment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.70
     Monfieur
    -0.66
     geodes
    -0.61
     Efq
    -0.61
     Sima
    -0.58
     whoſe
    -0.58
     Theſe
    -0.58
     Majefty
    -0.57
     Beſ
    -0.57
     Diſ
    -0.54
    POSITIVE LOGITS
     their
    0.80
     themselves
    0.79
    Spoljašnje
    0.65
    themselves
    0.63
     ihrer
    0.61
     ihrem
    0.61
     ihres
    0.60
    styleType
    0.59
    their
    0.58
     ihren
    0.58
    Act Density 0.528%

    No Known Activations