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

    Neuronpedia

    INDEX
    Explanations

    future-oriented verbs and phrases indicating potential actions or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sol
    -0.18
    idden
    -0.17
     Sparks
    -0.15
     SolidColorBrush
    -0.14
    ENA
    -0.14
     Alive
    -0.14
    illin
    -0.14
     pract
    -0.14
     associ
    -0.14
     disb
    -0.14
    POSITIVE LOGITS
     Forge
    0.16
     Zap
    0.16
     Chronicle
    0.16
    ids
    0.15
    637
    0.14
    _Float
    0.14
     Herald
    0.14
    529
    0.14
    481
    0.14
     Foster
    0.14
    Act Density 0.294%

    No Known Activations