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

    Neuronpedia

    INDEX
    Explanations

    words related to betrayal and treason

    oai_token-act-pair · gpt-3.5-turbo

    terms related to betrayal and treachery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aho
    -0.85
    nesota
    -0.84
    peed
    -0.73
    ascar
    -0.71
    ouf
    -0.69
    area
    -0.67
    sit
    -0.66
    aque
    -0.65
    occ
    -0.64
    iang
    -0.62
    POSITIVE LOGITS
     betray
    1.06
     betrayed
    0.90
     betrayal
    0.82
    esses
    0.70
    Ò
    0.67
     allegiance
    0.66
     sincere
    0.65
     Pact
    0.65
    ãĥĺ
    0.64
    ments
    0.64
    Act Density 0.016%

    No Known Activations