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

    Neuronpedia

    INDEX
    Explanations

    references to technology and user engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.26
     itſelf
    -1.17
     myſelf
    -1.17
     Monfieur
    -1.12
     صوتيه
    -1.07
     Majefty
    -1.03
     ſind
    -0.97
     Theſe
    -0.97
     Reſ
    -0.96
     Мексичка
    -0.95
    POSITIVE LOGITS
     or
    0.47
     (
    0.45
    .
    0.44
     
    0.44
     performance
    0.43
    ,
    0.42
     .
    0.41
     de
    0.39
     the
    0.38
     her
    0.37
    Act Density 0.581%

    No Known Activations