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

    Neuronpedia

    INDEX
    Explanations

    timestamps and time formatting patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Times in `HH:MM` or similar formats

    np_acts-logits-general · gemini-2.0-flash

    time formats (HH:mm:ss, h:mm a)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تانيه
    -0.56
    isContained
    -0.54
     autorytatywna
    -0.51
    postIndex
    -0.50
    
    -0.50
    SourceChecksum
    -0.49
    EndContext
    -0.48
     onAnimation
    -0.48
    hile
    -0.45
    chtenstein
    -0.44
    POSITIVE LOGITS
     hour
    1.15
     hours
    1.01
     hourly
    0.99
     HOUR
    0.94
    hour
    0.94
     Hourly
    0.88
     horaire
    0.86
     Hours
    0.86
    hours
    0.85
     HOURS
    0.84
    Act Density 0.338%

    No Known Activations