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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating age

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and age references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    btn
    -0.75
     Rica
    -0.74
    vell
    -0.71
    stadt
    -0.69
     oneself
    -0.68
     guiName
    -0.67
    olean
    -0.66
    ilst
    -0.62
     yourself
    -0.61
     himself
    -0.60
    POSITIVE LOGITS
     cents
    0.93
     predecessors
    0.93
    teenth
    0.88
     namesake
    0.88
     acres
    0.86
     counterparts
    0.86
     possessions
    0.79
     biggest
    0.75
     holdings
    0.74
     SHARES
    0.73
    Act Density 0.102%

    No Known Activations