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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edException
    -0.19
    ej
    -0.17
    aN
    -0.15
    orum
    -0.15
     Lair
    -0.14
    ries
    -0.13
    aan
    -0.13
    ties
    -0.13
     Hew
    -0.12
    tb
    -0.12
    POSITIVE LOGITS
    ftware
    0.35
    bsite
    0.34
    apons
    0.31
    ctrine
    0.30
    icipants
    0.30
    IGINAL
    0.30
    autiful
    0.29
    thing
    0.28
    ufact
    0.28
    enticate
    0.28
    Act Density 0.722%

    No Known Activations