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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures related to skill-based classifications or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -1.20
    AnchorStyles
    -1.17
     ་་
    -1.08
     photolibrary
    -0.99
     purpoſe
    -0.98
     gddr
    -0.97
     Houſe
    -0.97
    findpost
    -0.95
     iſt
    -0.94
    ">//
    -0.94
    POSITIVE LOGITS
     V
    0.74
     D
    0.73
     W
    0.73
     H
    0.73
     A
    0.72
     K
    0.72
     B
    0.71
     G
    0.70
     M
    0.69
     N
    0.67
    Act Density 0.631%

    No Known Activations