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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly those related to statistics and legislative references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.90
    wagen
    -0.89
    warm
    -0.85
    pring
    -0.83
    velength
    -0.82
    trak
    -0.79
     retard
    -0.78
    uten
    -0.76
    itism
    -0.75
     warmer
    -0.74
    POSITIVE LOGITS
    rd
    0.87
    shaw
    0.83
    helle
    0.73
    etr
    0.72
     Clicker
    0.68
    leness
    0.65
    uous
    0.64
    âĹ¼
    0.64
    olog
    0.63
    uously
    0.63
    Act Density 0.046%

    No Known Activations