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

    Neuronpedia

    INDEX
    Explanations

    technical terms and structures related to programming and coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -1.12
    DeleteBehavior
    -0.98
    GEBURTSDATUM
    -0.96
     ModelExpression
    -0.94
    istoitu
    -0.94
    LookAnd
    -0.93
    Personendaten
    -0.90
     MenuView
    -0.87
    TagMode
    -0.85
    ForValue
    -0.85
    POSITIVE LOGITS
    ®
    0.70
    <bos>
    0.69
    core
    0.63
    _
    0.59
     core
    0.55
    核心
    0.54
    typeof
    0.51
    <eos>
    0.51
     susi
    0.49
    ™
    0.49
    Act Density 0.669%

    No Known Activations