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

    Neuronpedia

    INDEX
    Explanations

    references to disparities or differences in conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Shou
    -0.74
     Roscoe
    -0.67
     ricordi
    -0.62
     procé
    -0.61
     Hodg
    -0.59
    tencent
    -0.56
    Aiheesta
    -0.55
     torchvision
    -0.55
     familiari
    -0.54
    rotu
    -0.53
    POSITIVE LOGITS
     gap
    4.10
     Gap
    3.70
    gap
    3.56
    Gap
    3.44
     gaps
    3.44
     Gaps
    3.28
    gaps
    2.96
     GAP
    2.71
    GAP
    2.31
    갭
    1.62
    Act Density 0.072%

    No Known Activations