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

    Neuronpedia

    INDEX
    Explanations

    possessive forms, particularly those indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wright
    -0.96
    urat
    -0.79
    staking
    -0.78
    oyle
    -0.75
    ourage
    -0.75
    ector
    -0.74
    handedly
    -0.74
    xual
    -0.74
    ayne
    -0.70
    76561
    -0.70
    POSITIVE LOGITS
     announcement
    0.86
     edition
    0.80
     Doodle
    0.79
     headlines
    0.76
     predicament
    0.74
     update
    0.74
     hottest
    0.74
     ze
    0.71
     episode
    0.69
     reckoning
    0.68
    Act Density 0.020%

    No Known Activations