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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ownership or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.04
     Majefty
    -0.89
     myſelf
    -0.86
     pleaſure
    -0.86
     fhort
    -0.85
     raiſ
    -0.84
     occaf
    -0.83
     Houſe
    -0.80
     Diſ
    -0.80
     Anſ
    -0.79
    POSITIVE LOGITS
     oldest
    0.81
     Amongst
    0.81
     dintre
    0.77
    oldest
    0.77
     nahilalakip
    0.76
     AMONG
    0.74
    BoxShadow
    0.72
    ństw
    0.71
    ății
    0.70
    Hentet
    0.69
    Act Density 0.138%

    No Known Activations