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

    Neuronpedia

    INDEX
    Explanations

    second person pronouns followed by verbs or verb phrases

    oai_token-act-pair · gpt-3.5-turbo

    the second-person perspective in statements directed at the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿½
    -0.76
     Cutter
    -0.62
    atory
    -0.62
    Materials
    -0.58
     Palest
    -0.58
     Gor
    -0.58
    OTOS
    -0.55
     Action
    -0.55
    atana
    -0.54
    REDACTED
    -0.54
    POSITIVE LOGITS
    're
    1.39
    'll
    1.35
     owe
    1.26
    've
    1.24
     MUST
    1.19
     gotta
    1.13
     SHOULD
    1.13
     probably
    1.12
     ought
    1.11
     shouldn
    1.10
    Act Density 0.095%

    No Known Activations