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

    Neuronpedia

    INDEX
    Explanations

    times expressed in minutes and times of the day

    oai_token-act-pair · gpt-3.5-turbo

    periods of time denoted by specific hour references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mara
    -0.64
    enegger
    -0.61
     Maw
    -0.59
     fors
    -0.58
     Levin
    -0.58
     spo
    -0.58
     execut
    -0.57
     persecuted
    -0.57
     resemb
    -0.57
     tsun
    -0.56
    POSITIVE LOGITS
    pm
    0.74
    meter
    0.72
    gran
    0.71
    1500
    0.71
    cation
    0.70
    olitics
    0.69
    Downloadha
    0.69
    date
    0.69
    level
    0.69
     apiece
    0.68
    Act Density 0.025%

    No Known Activations