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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude or good wishes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to blessings and curses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighters
    -0.77
    izoph
    -0.76
    raper
    -0.76
    isting
    -0.73
    Nazi
    -0.72
    regor
    -0.72
    WAR
    -0.70
    pta
    -0.70
    oxic
    -0.70
    PRES
    -0.68
    POSITIVE LOGITS
     blessings
    0.93
     Bless
    0.90
     bestowed
    0.88
     bless
    0.84
     Almighty
    0.82
     blessing
    0.81
     blessed
    0.78
    fully
    0.77
     curse
    0.75
     forgiveness
    0.75
    Act Density 0.057%

    No Known Activations