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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verbs related to personal actions, especially in a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    references to the subject "he" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earch
    -0.77
    arsity
    -0.69
    ormal
    -0.63
    berra
    -0.62
    ienne
    -0.62
    atlantic
    -0.62
    rame
    -0.61
    ãĥ©ãĥ³
    -0.61
    Prem
    -0.61
    ullivan
    -0.59
    POSITIVE LOGITS
    'll
    1.10
    'd
    1.08
    've
    0.94
     knew
    0.90
    're
    0.89
     didnt
    0.86
     drank
    0.85
     wandered
    0.84
     encount
    0.83
     wand
    0.83
    Act Density 0.700%

    No Known Activations