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

    Neuronpedia

    INDEX
    Explanations

    evaluations of events or experiences in a positive or negative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lest
    -0.15
     rather
    -0.15
    antal
    -0.15
     bore
    -0.15
    else
    -0.15
    amen
    -0.14
    lol
    -0.14
     tantal
    -0.14
    ipples
    -0.14
    raison
    -0.14
    POSITIVE LOGITS
     overall
    0.31
     especially
    0.27
     considering
    0.26
    overall
    0.26
    especially
    0.24
    Overall
    0.23
     Overall
    0.23
     especialmente
    0.22
     оÑģобенно
    0.20
     altogether
    0.19
    Act Density 0.253%

    No Known Activations