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

    Neuronpedia

    INDEX
    Explanations

    duplicates or similarities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of identicality or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stra
    -0.74
    raq
    -0.72
    ================================================================
    -0.70
    Explore
    -0.67
    âĵĺ
    -0.66
    bane
    -0.65
    Pal
    -0.65
    Fan
    -0.65
    veland
    -0.64
    HI
    -0.62
    POSITIVE LOGITS
     twins
    1.21
     twin
    0.99
    icut
    0.88
    etrical
    0.83
    lihood
    0.83
     identical
    0.81
    minded
    0.74
     pairs
    0.73
    etry
    0.72
     sized
    0.71
    Act Density 0.036%

    No Known Activations