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

    Neuronpedia

    INDEX
    Explanations

    words related to malevolent or sinister concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of evil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dropping
    -0.78
    eding
    -0.78
    phrine
    -0.77
    akeru
    -0.76
    GN
    -0.74
    UNCH
    -0.72
    aro
    -0.71
    ribe
    -0.71
    raltar
    -0.71
    illation
    -0.71
    POSITIVE LOGITS
     deeds
    0.96
     deed
    0.93
     incarn
    0.92
     twin
    0.89
     mastermind
    0.84
    nesses
    0.83
     genius
    0.80
    NESS
    0.79
     empire
    0.76
     lord
    0.76
    Act Density 0.034%

    No Known Activations