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

    Neuronpedia

    INDEX
    Explanations

    first person singular verbs related to observation and perception

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Regarding
    -0.90
    arranted
    -0.89
    "},"
    -0.86
    âĹ¼
    -0.86
    Regarding
    -0.86
     âĨij
    -0.85
    null
    -0.85
    Considering
    -0.84
    \"
    -0.83
    Overall
    -0.82
    POSITIVE LOGITS
     everywhere
    0.94
     friendships
    0.86
     everything
    0.81
     grit
    0.79
     endless
    0.79
     malls
    0.79
     roar
    0.78
     sweat
    0.78
     empires
    0.76
     rhythms
    0.75
    Act Density 0.808%

    No Known Activations