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

    Neuronpedia

    INDEX
    Explanations

    references to the term "This" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Италијани
    -0.88
    IUrlHelper
    -0.85
    SBATCH
    -0.76
     فريبيس
    -0.75
    verwijspagina
    -0.74
     ویکی‌پدی
    -0.73
    oneofs
    -0.72
    adaptiveStyles
    -0.68
     صوتيه
    -0.68
    featureID
    -0.68
    POSITIVE LOGITS
    This
    0.83
     This
    0.82
    That
    0.56
     is
    0.55
     Dieser
    0.53
     That
    0.50
     has
    0.49
     was
    0.48
    which
    0.45
    These
    0.45
    Act Density 0.198%

    No Known Activations