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

    Neuronpedia

    INDEX
    Explanations

    conclusions or summaries presented in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollectionView
    -0.66
    بوابة
    -0.64
     <=",
    -0.62
    AnchorStyles
    -0.61
    rateur
    -0.59
    TemporalType
    -0.59
    MLLoader
    -0.59
    giveness
    -0.58
    Portale
    -0.58
     sometimes
    -0.58
    POSITIVE LOGITS
    Furthermore
    1.43
    Moreover
    1.42
     Furthermore
    1.38
    However
    1.37
     However
    1.35
     Moreover
    1.35
    Therefore
    1.28
     Therefore
    1.27
    Additionally
    1.27
    Fortunately
    1.22
    Act Density 0.300%

    No Known Activations