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

    Neuronpedia

    INDEX
    Explanations

    specific non-English characters or tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.03
    Tikang
    -1.01
     iconFacebook
    -0.97
     iſt
    -0.91
    ंदीखरीदारी
    -0.89
     ་་
    -0.88
     itſelf
    -0.88
     ―――
    -0.88
    kloped
    -0.83
     Numerade
    -0.82
    POSITIVE LOGITS
     K
    1.03
     Z
    1.03
     P
    1.02
     W
    0.99
    setH
    0.96
     M
    0.96
     L
    0.94
    setP
    0.93
     S
    0.91
     O
    0.91
    Act Density 0.081%

    No Known Activations