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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "I" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    pronouns, particularly first and second person pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hok
    -0.67
    hap
    -0.66
    elta
    -0.64
     Wake
    -0.61
    VK
    -0.60
     Seah
    -0.57
    detail
    -0.54
     Anchorage
    -0.54
     Void
    -0.53
     bud
    -0.52
    POSITIVE LOGITS
    'll
    0.71
    cius
    0.69
     surely
    0.66
    izons
    0.65
    taboola
    0.62
    $,
    0.61
     wont
    0.61
    eded
    0.60
    stals
    0.59
    ulia
    0.58
    Act Density 0.166%

    No Known Activations