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

    Neuronpedia

    INDEX
    Explanations

    mentions of friendships or relationships with other people

    oai_token-act-pair · gpt-3.5-turbo

    repetitive mentions of friendship or connections among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    case
    -0.71
    cases
    -0.69
     scenarios
    -0.63
    TRY
    -0.62
    heny
    -0.61
    ahead
    -0.60
     percentages
    -0.60
     levels
    -0.59
     doses
    -0.58
    MX
    -0.58
    POSITIVE LOGITS
     mine
    1.97
     ours
    1.92
     hers
    1.88
     yours
    1.70
     theirs
    1.66
     sorts
    1.27
     Mine
    1.17
    Mine
    0.81
     Nanto
    0.74
     course
    0.74
    Act Density 0.136%

    No Known Activations