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

    Neuronpedia

    INDEX
    Explanations

    comparisons or similarities using the word "like."

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or analogies using "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etts
    -0.76
    ulet
    -0.74
    atis
    -0.72
    Published
    -0.71
    mt
    -0.68
    ells
    -0.67
    Catal
    -0.67
    rift
    -0.66
    ilic
    -0.66
    uers
    -0.64
    POSITIVE LOGITS
    lihood
    1.48
    lier
    0.93
     ours
    0.89
     minded
    0.73
    liest
    0.73
    minded
    0.73
    liness
    0.70
     wildfire
    0.70
    soDeliveryDate
    0.68
     yours
    0.66
    Act Density 0.042%

    No Known Activations