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

    Neuronpedia

    INDEX
    Explanations

    comparisons or similarities

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases that express similarity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Limited
    -0.76
    atis
    -0.73
    ulet
    -0.73
    ALE
    -0.72
    inion
    -0.71
    rift
    -0.70
    Ve
    -0.68
    UU
    -0.67
    bern
    -0.66
    duction
    -0.66
    POSITIVE LOGITS
    lihood
    1.38
    lier
    0.93
     ours
    0.90
     minded
    0.78
    liness
    0.71
    minded
    0.70
     fate
    0.68
    soDeliveryDate
    0.68
    liest
    0.67
     counterparts
    0.66
    Act Density 0.034%

    No Known Activations