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

    Neuronpedia

    INDEX
    Explanations

    technical terms and keywords related to programming and data handling within configurations and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.60
     of
    -0.53
     Anda
    -0.52
     me
    -0.49
     Dr
    -0.49
     K
    -0.48
    ?
    -0.48
     F
    -0.47
     a
    -0.47
     ter
    -0.46
    POSITIVE LOGITS
     للمعارف
    1.05
     Efq
    0.99
     Theſe
    0.98
    theless
    0.94
     Diſ
    0.89
     Majefty
    0.87
     Chriſt
    0.86
    ⓧ
    0.85
     Houſe
    0.85
     Monfieur
    0.85
    Act Density 0.681%

    No Known Activations