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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs related to actions or states

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating possession or performative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.80
    amaz
    -0.70
    itive
    -0.68
    aukee
    -0.66
    classic
    -0.63
    ibaba
    -0.63
    ieties
    -0.62
     Atkinson
    -0.62
    į
    -0.61
    downs
    -0.61
    POSITIVE LOGITS
    'll
    1.04
    'd
    1.02
     could
    0.96
    're
    0.93
    've
    0.92
     should
    0.90
     ought
    0.90
     shouldn
    0.88
     cannot
    0.87
     might
    0.85
    Act Density 0.261%

    No Known Activations