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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases expressing or questioning opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.15
     esternos
    -1.01
     فريبيس
    -0.93
    ConstraintMaker
    -0.92
     متعلقه
    -0.92
     للاسماء
    -0.83
     विश्वसनीयता
    -0.83
    BeginContext
    -0.83
     resourceCulture
    -0.82
     Monfieur
    -0.78
    POSITIVE LOGITS
    +#+
    0.57
     Gegen
    0.47
     in
    0.46
    rej
    0.45
     as
    0.43
    WebMethod
    0.42
    colgroup
    0.42
     here
    0.41
     
    0.41
     indeed
    0.40
    Act Density 0.287%

    No Known Activations