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

    Neuronpedia

    INDEX
    Explanations

    references to knowledge and understanding of details, particularly in specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urette
    -0.18
    gili
    -0.15
    #__
    -0.15
    .BL
    -0.14
    éo
    -0.14
    arton
    -0.14
    ÏĢοÏħ
    -0.14
    WithDuration
    -0.13
    _PAD
    -0.13
    nown
    -0.13
    POSITIVE LOGITS
     intimately
    0.47
     better
    0.41
     well
    0.40
     intimate
    0.35
     firsthand
    0.32
    better
    0.31
    well
    0.28
     mieux
    0.27
     intim
    0.27
     backwards
    0.27
    Act Density 0.162%

    No Known Activations