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

    Neuronpedia

    INDEX
    Explanations

    words related to strong negative emotions or situations

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases associated with bitterness or negative emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utations
    -0.81
    amera
    -0.73
    ustainable
    -0.71
    uters
    -0.69
    apan
    -0.68
    utation
    -0.68
    arlane
    -0.68
    udeau
    -0.68
    apon
    -0.67
    ulhu
    -0.67
    POSITIVE LOGITS
     rivalry
    0.91
     bitter
    0.89
     rival
    0.88
     battle
    0.86
     thorn
    0.85
     quarrel
    0.85
    terness
    0.85
     disputes
    0.84
    cest
    0.83
     dispute
    0.81
    Act Density 0.137%

    No Known Activations