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

    Neuronpedia

    INDEX
    Explanations

    phrases related to betrayal

    oai_token-act-pair · gpt-3.5-turbo

    words and themes related to betrayal and deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.88
    nets
    -0.79
    aho
    -0.76
    lining
    -0.73
    ifying
    -0.72
    ums
    -0.72
    umin
    -0.72
    ULAR
    -0.69
    ifiers
    -0.69
    ocating
    -0.68
    POSITIVE LOGITS
    cipled
    0.86
     loyalty
    0.78
     oath
    0.76
     allegiance
    0.76
    edience
    0.74
     compass
    0.73
     betray
    0.73
    warm
    0.72
     kindness
    0.70
     jer
    0.68
    Act Density 0.101%

    No Known Activations