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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to specific periods or durations of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hedral
    -0.63
     debit
    -0.62
     reconc
    -0.61
     insign
    -0.60
     fingert
    -0.60
     faint
    -0.60
     fisherman
    -0.59
    oké
    -0.59
    Tonight
    -0.59
    ilater
    -0.58
    POSITIVE LOGITS
    frames
    0.96
    lot
    0.92
     period
    0.90
     span
    0.89
    period
    0.84
    outs
    0.82
     periods
    0.79
     frame
    0.77
    SPONSORED
    0.77
    nings
    0.77
    Act Density 0.071%

    No Known Activations