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

    Neuronpedia

    INDEX
    Explanations

    brief mentions or descriptions within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "brief."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceans
    -0.80
    âĹ¼
    -0.70
    Train
    -0.69
    SEA
    -0.69
    çĶ°
    -0.68
     Polo
    -0.68
    GO
    -0.68
    JV
    -0.68
    IVER
    -0.66
    MIC
    -0.66
    POSITIVE LOGITS
    cases
    1.38
    case
    1.27
     stint
    0.91
     glimps
    0.88
    erate
    0.88
    itud
    0.83
    aneously
    0.79
    ebin
    0.78
     bursts
    0.77
    ener
    0.76
    Act Density 0.021%

    No Known Activations