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

    Neuronpedia

    INDEX
    Explanations

    pphrases describing forceful physical actions

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases using the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiba
    -0.85
    ulty
    -0.82
    inion
    -0.79
    iets
    -0.79
    alf
    -0.74
    ilic
    -0.72
    oard
    -0.70
    endiary
    -0.69
    omsky
    -0.68
    ourse
    -0.68
    POSITIVE LOGITS
    lihood
    1.56
    lier
    1.09
    liest
    1.08
     wildfire
    0.87
    liness
    0.85
     ours
    0.80
     clock
    0.79
     minded
    0.77
    minded
    0.77
     crazy
    0.69
    Act Density 0.082%

    No Known Activations