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

    Neuronpedia

    INDEX
    Explanations

    dates and temporal references

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time markers or temporal phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artifacts
    -0.66
     honored
    -0.62
     Nanto
    -0.61
    jri
    -0.61
    ARI
    -0.61
     prosec
    -0.60
     prosecuted
    -0.60
     hesitate
    -0.59
     guided
    -0.59
    imir
    -0.58
    POSITIVE LOGITS
     standards
    0.75
    stocks
    0.72
    rox
    0.67
    century
    0.67
     exhaustion
    0.66
    End
    0.65
    Closure
    0.65
    ä¸ī
    0.65
    thirds
    0.64
    end
    0.62
    Act Density 0.085%

    No Known Activations