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

    Neuronpedia

    INDEX
    Explanations

    sentences ending in periods

    oai_token-act-pair · gpt-3.5-turbo

    sentences with high emotional or dramatic emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     transact
    -0.70
     detainees
    -0.69
    apers
    -0.67
     overlap
    -0.67
     inherited
    -0.67
     sidx
    -0.66
    ieth
    -0.66
     analysts
    -0.66
     kidn
    -0.65
     negoti
    -0.65
    POSITIVE LOGITS
     Turns
    1.69
     Luckily
    1.25
    Fast
    1.20
     Thankfully
    1.18
    Luckily
    1.11
     Eventually
    1.10
     Unfortunately
    1.09
    Thankfully
    1.09
     Needless
    1.08
     Surprisingly
    1.07
    Act Density 0.486%

    No Known Activations