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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing types or categories of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.72
    Atsauces
    -0.58
     CreateTagHelper
    -0.55
    queryInterface
    -0.54
     withdrew
    -0.54
     VIDEOTAPE
    -0.51
    dailymail
    -0.50
    NotBlank
    -0.49
    Hauptartikel
    -0.49
    +#+#
    -0.49
    POSITIVE LOGITS
     solche
    0.97
     solchen
    0.87
     solcher
    0.81
     sowas
    0.80
    ConstraintMaker
    0.79
     such
    0.78
    Such
    0.74
    这类
    0.73
     Такие
    0.73
    こういう
    0.71
    Act Density 0.305%

    No Known Activations