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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms typically used in technical or professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.96
     myſelf
    -0.79
     faſt
    -0.77
    #+#
    -0.73
    AnchorStyles
    -0.72
     Songtext
    -0.72
     ſind
    -0.72
     ་་
    -0.71
    HomeAsUpEnabled
    -0.70
     themſelves
    -0.70
    POSITIVE LOGITS
     G
    1.08
     M
    1.04
     K
    1.03
     R
    1.02
     S
    1.01
     W
    0.99
     H
    0.99
     L
    0.98
     B
    0.97
     P
    0.96
    Act Density 0.685%

    No Known Activations