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

    Neuronpedia

    INDEX
    Explanations

    complex conditional statements or scenarios in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \{\\
    -0.84
    HasAnnotation
    -0.64
    atteindre
    -0.62
     initComponents
    -0.60
     Könige
    -0.59
     TAMBIÉN
    -0.58
    λοι
    -0.57
     الحره
    -0.57
    ◝
    -0.56
    plish
    -0.56
    POSITIVE LOGITS
    CreateModel
    0.60
     Erişim
    0.58
    Diweddarwch
    0.54
    ⓧ
    0.51
    SourceChecksum
    0.51
    <bos>
    0.50
    却是
    0.50
    السكان
    0.49
    }])
    0.49
    ])).
    0.48
    Act Density 1.425%

    No Known Activations