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

    Neuronpedia

    INDEX
    Explanations

    words that express lasting or enduring qualities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    words related to lasting qualities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hops
    -0.87
    asers
    -0.82
    eah
    -0.81
    ©¶æ
    -0.80
    pta
    -0.80
    aped
    -0.77
    rera
    -0.76
    outing
    -0.73
    anders
    -0.72
    uden
    -0.72
    POSITIVE LOGITS
    ly
    1.09
    stone
    0.83
    LY
    0.78
    theless
    0.76
     mysteries
    0.74
    lies
    0.73
    stones
    0.73
    essential
    0.72
    wealth
    0.72
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.71
    Act Density 0.019%

    No Known Activations