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

    Neuronpedia

    INDEX
    Explanations

    phrases or words referencing significant occurrences or happenings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geon
    -0.85
    ãĤĮ
    -0.72
    artisan
    -0.70
    ench
    -0.66
    arton
    -0.64
    aband
    -0.64
    PLA
    -0.62
     Mines
    -0.62
    otto
    -0.62
    dit
    -0.62
    POSITIVE LOGITS
     transpired
    1.28
     unfold
    1.24
     unfolded
    1.21
     unfolding
    1.19
    uate
    1.06
     occurring
    1.04
    uating
    0.97
     occurred
    0.95
     happening
    0.95
     horizon
    0.91
    Act Density 0.025%

    No Known Activations