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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and their relationships, particularly in equations or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ་་
    -1.23
     Theſe
    -1.17
     ―――――
    -1.09
    )");
    -1.08
     myſelf
    -1.05
     Anſ
    -1.05
     iſt
    -1.04
     ſind
    -1.02
     Beſ
    -1.02
     ſeveral
    -1.01
    POSITIVE LOGITS
     S
    1.13
     d
    1.13
     P
    1.11
     p
    1.08
     r
    1.08
     b
    1.05
     K
    1.05
     L
    1.05
     s
    1.04
     W
    1.04
    Act Density 1.782%

    No Known Activations