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

    Neuronpedia

    INDEX
    Explanations

    words associated with recovery and replenishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TW
    -0.75
    MSN
    -0.73
    jun
    -0.71
    fuck
    -0.69
    adiq
    -0.67
     Nig
    -0.67
    phen
    -0.66
    hole
    -0.66
    atan
    -0.62
    gey
    -0.62
    POSITIVE LOGITS
    ishable
    0.88
     stale
    0.77
    igate
    0.76
     depleted
    0.74
     unused
    0.73
    ursed
    0.73
     depot
    0.72
     recycle
    0.71
    ilitating
    0.71
    lict
    0.70
    Act Density 0.056%

    No Known Activations