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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases indicating causation or progression

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
    blocking
    -0.57
    DERR
    -0.53
    NF
    -0.52
     bachelor
    -0.52
    rals
    -0.52
     presentation
    -0.51
     Altern
    -0.51
     DISTRICT
    -0.50
    ãĥ¯ãĥ³
    -0.49
    POSITIVE LOGITS
    bered
    1.17
    oner
    1.10
    apy
    0.93
    ooo
    0.88
     far
    0.88
    oths
    0.84
    othe
    0.83
    oooo
    0.82
     much
    0.82
    assi
    0.81
    Act Density 0.062%

    No Known Activations