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

    Neuronpedia

    INDEX
    Explanations

    terms related to separation or division

    oai_token-act-pair · gpt-3.5-turbo

    terms related to separation or division

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inel
    -0.90
    psc
    -0.88
    anamo
    -0.79
    odium
    -0.75
    aina
    -0.72
    enez
    -0.72
    kinson
    -0.71
    kson
    -0.70
    azor
    -0.69
    lev
    -0.69
    POSITIVE LOGITS
     partition
    1.08
     partitions
    1.06
     Tsukuyomi
    0.78
     divid
    0.77
    ãĥ¼ãĥĨ
    0.75
    ipation
    0.74
     flares
    0.74
    naire
    0.73
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.72
     ãĤµ
    0.71
    Act Density 0.009%

    No Known Activations