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

    Neuronpedia

    INDEX
    Explanations

    words related to attractiveness or desirability

    oai_token-act-pair · gpt-3.5-turbo

    terms related to desirability or appeal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cedented
    -0.96
    avia
    -0.83
    chu
    -0.81
    othing
    -0.80
     respecting
    -0.78
    othe
    -0.77
    rel
    -0.76
    blance
    -0.76
    bel
    -0.75
    algia
    -0.72
    POSITIVE LOGITS
     prospects
    1.11
     prospect
    1.04
     alternatives
    0.97
     proposition
    0.96
     targets
    0.96
     candidates
    0.84
     alternative
    0.81
     prey
    0.80
     options
    0.76
     destinations
    0.76
    Act Density 0.126%

    No Known Activations