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

    Neuronpedia

    INDEX
    Explanations

    verbs related to pardoning or excusing someone's actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of forgiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anto
    -0.81
    eding
    -0.75
    rus
    -0.73
    urg
    -0.73
    weeney
    -0.71
    ulhu
    -0.71
    anooga
    -0.68
     Dew
    -0.67
    rush
    -0.66
    abbage
    -0.66
    POSITIVE LOGITS
     forgiven
    1.56
     forgiveness
    1.30
     forgive
    1.25
     pard
    0.96
     forgiving
    0.95
     pardon
    0.93
    give
    0.91
     msec
    0.86
     forg
    0.86
     "$:/
    0.83
    Act Density 0.008%

    No Known Activations