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

    Neuronpedia

    INDEX
    Explanations

    comparisons indicated by the word "Unlike"

    oai_token-act-pair · gpt-3.5-turbo

    instances of comparison phrases that begin with "Unlike."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gae
    -0.77
    essen
    -0.76
    hiba
    -0.73
    adel
    -0.67
    anut
    -0.65
    idates
    -0.65
    ells
    -0.65
    è¦ļéĨĴ
    -0.65
    urry
    -0.65
    isition
    -0.64
    POSITIVE LOGITS
    lihood
    1.40
    liest
    1.04
    ly
    0.88
     ours
    0.85
    liness
    0.79
    lier
    0.78
     minded
    0.77
    minded
    0.73
    entimes
    0.72
    Ħ¢
    0.69
    Act Density 0.020%

    No Known Activations