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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress, change, and action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.68
    izens
    -0.66
    hattan
    -0.61
     descended
    -0.60
     Cheong
    -0.60
    illon
    -0.60
    lement
    -0.59
     fut
    -0.58
     nostalg
    -0.58
    ilial
    -0.57
    POSITIVE LOGITS
     ASAP
    0.83
     quicker
    0.75
     cheaply
    0.72
     sooner
    0.71
    osc
    0.66
     Madden
    0.64
     easier
    0.62
    office
    0.62
     correct
    0.62
    road
    0.61
    Act Density 0.137%

    No Known Activations