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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    832
    -0.17
    411
    -0.17
    azi
    -0.15
    rama
    -0.14
    nar
    -0.14
    song
    -0.14
    άζ
    -0.14
    616
    -0.14
    ocity
    -0.14
    393
    -0.14
    POSITIVE LOGITS
    iot
    0.16
     Dumpster
    0.15
    äºľ
    0.14
    etsk
    0.14
    enic
    0.14
     Cham
    0.14
    PropTypes
    0.14
    ħ
    0.14
    iso
    0.13
    æĿ
    0.13
    Act Density 0.459%

    No Known Activations