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

    Neuronpedia

    INDEX
    Explanations

    XML or structured data related to applications and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wik
    -0.17
    ’T
    -0.15
    '].$
    -0.14
    erra
    -0.14
    !).↵↵
    -0.14
     Brill
    -0.14
    />.↵↵
    -0.14
     ;č↵
    -0.14
     Denn
    -0.14
    pong
    -0.13
    POSITIVE LOGITS
    "encoding
    0.19
    encoding
    0.19
    "
    0.18
    _utf
    0.18
    _encoding
    0.16
     encoding
    0.15
    Encoding
    0.15
     ε
    0.15
     enc
    0.15
    oger
    0.15
    Act Density 0.007%

    No Known Activations