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

    Neuronpedia

    INDEX
    Explanations

    programmatic structures and error handling related to Just-In-Time (JIT) compilation in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    TagMode
    -0.77
    <eos>
    -0.63
     
    -0.63
    __(/*!
    -0.60
    localctx
    -0.56
    HasColumnType
    -0.56
    RLock
    -0.54
     super
    -0.54
    EditorBrowsable
    -0.54
    IUrlHelper
    -0.52
    POSITIVE LOGITS
     houſe
    1.00
     pleaſure
    0.99
    neſs
    0.90
     purpoſe
    0.90
     Diſ
    0.88
     perſon
    0.88
     Reſ
    0.88
     Anſ
    0.86
     myſelf
    0.86
    ſelf
    0.86
    Act Density 9.064%

    No Known Activations