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

    Neuronpedia

    INDEX
    Explanations

    phrases implying a comparison to something else

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating similarity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aster
    -0.72
     Derby
    -0.72
     Mush
    -0.69
     Ventura
    -0.69
     Bild
    -0.69
     Fre
    -0.67
    /+
    -0.66
    Query
    -0.64
     Ãĸ
    -0.64
     Ramsey
    -0.63
    POSITIVE LOGITS
     situated
    1.25
     minded
    1.10
    minded
    0.95
     inclined
    0.91
    etheless
    0.90
    inki
    0.86
    sit
    0.85
     sized
    0.83
    quartered
    0.82
    wcs
    0.82
    Act Density 0.009%

    No Known Activations