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

    Neuronpedia

    INDEX
    Explanations

    keywords related to negotiations or discussions between different parties

    oai_token-act-pair · gpt-3.5-turbo

    references to negotiations or interactions between different parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGR
    -0.80
    gn
    -0.78
    spect
    -0.78
    gow
    -0.76
    inav
    -0.76
    bably
    -0.75
    oultry
    -0.73
    imation
    -0.73
    rak
    -0.72
    igl
    -0.72
    POSITIVE LOGITS
     strangers
    0.77
     Israelis
    0.76
    between
    0.74
     sexes
    0.73
     factions
    0.73
     genders
    0.72
     spouses
    0.71
     combatants
    0.71
     Chancellor
    0.70
     friends
    0.69
    Act Density 0.041%

    No Known Activations