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

    Neuronpedia

    INDEX
    Explanations

    phrases describing actions or improvements related to personal belongings or domains

    oai_token-act-pair · gpt-3.5-turbo

    the possessive pronoun "your" in reference to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilts
    -0.80
    ĸļ
    -0.79
    perse
    -0.76
    apo
    -0.75
    vous
    -0.74
     Canaver
    -0.73
    itud
    -0.73
     apiece
    -0.68
    abl
    -0.68
    erald
    -0.66
    POSITIVE LOGITS
     own
    1.44
     favorite
    1.29
     favourite
    1.24
     opponent
    1.06
     surroundings
    1.03
    ocard
    1.01
     adversary
    0.98
     OWN
    0.95
     workspace
    0.94
     spouse
    0.94
    Act Density 0.132%

    No Known Activations