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

    Neuronpedia

    INDEX
    Explanations

    similes describing forceful or rough actions

    oai_token-act-pair · gpt-3.5-turbo

    similes and comparisons involving the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inion
    -0.82
    iets
    -0.81
    ulty
    -0.79
    hiba
    -0.77
    ilic
    -0.77
    elin
    -0.74
    ennes
    -0.71
    arcity
    -0.70
    inas
    -0.69
    ysical
    -0.69
    POSITIVE LOGITS
    lihood
    1.35
    liest
    1.04
    lier
    1.01
     clock
    0.86
     crazy
    0.85
     ours
    0.81
    liness
    0.80
     wildfire
    0.79
     minded
    0.75
    minded
    0.74
    Act Density 0.071%

    No Known Activations