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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verbs related to communication

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or reflections on experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orem
    -0.64
     2022
    -0.62
     arithmetic
    -0.60
     urgently
    -0.59
     miracle
    -0.58
    atories
    -0.57
     Clause
    -0.55
    Eight
    -0.54
     2024
    -0.54
     inscribed
    -0.54
    POSITIVE LOGITS
     kinda
    1.07
     alot
    1.00
     haha
    0.96
     maybe
    0.82
     doesnt
    0.82
     whats
    0.81
    laughs
    0.81
    Anyway
    0.80
     didnt
    0.79
     anyways
    0.76
    Act Density 1.295%

    No Known Activations