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

    Neuronpedia

    INDEX
    Explanations

    words related to conflicts, disagreements, and rifts between individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to conflict and divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anish
    -0.78
    elta
    -0.77
    oken
    -0.75
    icrobial
    -0.73
    ctors
    -0.71
    onut
    -0.71
    hetics
    -0.70
    azel
    -0.70
    urus
    -0.69
    recomm
    -0.67
    POSITIVE LOGITS
     flared
    1.09
     feud
    1.01
     raging
    0.93
     tensions
    0.88
     flare
    0.87
     factions
    0.87
     disagreements
    0.84
     brewing
    0.82
     disagreement
    0.82
     standoff
    0.82
    Act Density 0.146%

    No Known Activations