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

    Neuronpedia

    INDEX
    Explanations

    comparisons between the positive and negative aspects of different situations

    oai_token-act-pair · gpt-3.5-turbo

    contrasting situations or dualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.62
    started
    -0.59
    JD
    -0.59
     Tradable
    -0.57
    meet
    -0.57
    ģĸ
    -0.56
    uca
    -0.56
     enthusi
    -0.55
    worm
    -0.55
    Cho
    -0.55
    POSITIVE LOGITS
     hers
    0.96
     theirs
    0.89
     ones
    0.87
     ours
    0.87
     yours
    0.82
     mine
    0.80
     Ones
    0.73
    ;}
    0.65
    ossal
    0.62
    ample
    0.60
    Act Density 1.399%

    No Known Activations