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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and interactions

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and phrases indicating personal relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATIVE
    -0.70
    Thumbnail
    -0.70
    ãĥ¯
    -0.70
    vertisement
    -0.69
    ably
    -0.66
    arnaev
    -0.63
    ital
    -0.63
    icle
    -0.63
    entary
    -0.62
    lete
    -0.61
    POSITIVE LOGITS
     wanted
    0.98
     wanna
    0.98
     smelled
    0.93
     wished
    0.90
    'd
    0.89
     overheard
    0.88
     loved
    0.87
     sorry
    0.86
     loves
    0.85
     didnt
    0.85
    Act Density 0.212%

    No Known Activations