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

    Neuronpedia

    INDEX
    Explanations

    expressions related to variable assignments in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ་་
    -1.15
     myſelf
    -1.13
     ―――――
    -1.09
     ſind
    -1.04
     Theſe
    -1.01
     themſelves
    -0.99
     Beſ
    -0.98
     doubtnut
    -0.98
     iſt
    -0.97
    ſelf
    -0.97
    POSITIVE LOGITS
     h
    1.59
     H
    1.56
    H
    1.42
    setH
    1.31
    h
    1.22
     l
    1.03
     d
    1.00
     W
    0.99
     M
    0.99
     S
    0.98
    Act Density 0.131%

    No Known Activations