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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs indicating personal actions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal feelings and self-perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Need
    -0.67
    ij士
    -0.67
    OTOS
    -0.66
    Missing
    -0.66
     Bei
    -0.65
    CHAT
    -0.64
    ousands
    -0.63
    VW
    -0.63
    artifacts
    -0.63
     Bugs
    -0.62
    POSITIVE LOGITS
     phr
    1.10
     handled
    1.08
     treated
    0.98
     behaved
    0.96
     behave
    0.95
     interacts
    0.95
     dealt
    0.93
     interact
    0.90
     treat
    0.90
     pronounce
    0.89
    Act Density 0.186%

    No Known Activations