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

    Neuronpedia

    INDEX
    Explanations

    references to social media followers and engagement metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ew
    -0.17
    izik
    -0.16
    abble
    -0.15
    ters
    -0.15
    wap
    -0.14
    çĦ¼
    -0.14
    loth
    -0.14
    ffen
    -0.14
    ắn
    -0.14
    ocol
    -0.14
    POSITIVE LOGITS
     Legs
    0.17
    StatusLabel
    0.15
     éĥ
    0.14
    .BLL
    0.13
    onna
    0.13
    égor
    0.13
    FSIZE
    0.13
    TAIL
    0.13
    izophren
    0.13
    ati
    0.13
    Act Density 0.011%

    No Known Activations