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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns indicating direct address or reference in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.17
    ost
    -0.16
     Hyp
    -0.14
    ipe
    -0.14
     hypo
    -0.14
     manuscript
    -0.14
    628
    -0.14
    agog
    -0.14
     provid
    -0.14
    bn
    -0.13
    POSITIVE LOGITS
    tsy
    0.17
    luet
    0.16
    bia
    0.15
    ailable
    0.15
    seau
    0.15
    adecimal
    0.14
    tual
    0.14
    orton
    0.14
    ÏģÏīν
    0.14
    _require
    0.14
    Act Density 0.058%

    No Known Activations