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

    Neuronpedia

    INDEX
    Explanations

    references to time-based events or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.49
    ########.
    -0.46
    adaptiveStyles
    -0.38
    SpringRunner
    -0.38
     articles
    -0.36
    SBATCH
    -0.35
     createdBy
    -0.35
    日々
    -0.35
    openzeppelin
    -0.35
     createSlice
    -0.35
    POSITIVE LOGITS
     midway
    0.97
     penultimate
    0.84
     halfway
    0.81
     late
    0.79
    後半
    0.78
     early
    0.70
    early
    0.69
     mid
    0.69
    late
    0.69
     final
    0.68
    Act Density 0.587%

    No Known Activations