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

    Neuronpedia

    INDEX
    Explanations

    the frequency of first-person pronouns and expressions of personal experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DataURL
    -0.15
     Rahman
    -0.14
    972
    -0.14
    undef
    -0.14
    ="../../../
    -0.14
    greg
    -0.14
     ache
    -0.13
    ãģķãģ¾
    -0.13
    ÙĨدا
    -0.13
    okable
    -0.13
    POSITIVE LOGITS
     def
    0.20
     seen
    0.19
     rarity
    0.17
     barley
    0.17
     Dont
    0.17
     Seen
    0.15
     noticed
    0.15
    Ñī
    0.15
    ve
    0.15
     meant
    0.15
    Act Density 0.251%

    No Known Activations