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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate intention or desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resi
    -0.17
    elian
    -0.15
    endi
    -0.15
    shan
    -0.15
    tsy
    -0.15
    umer
    -0.14
    uin
    -0.14
    iants
    -0.14
    /OR
    -0.14
    arian
    -0.13
    POSITIVE LOGITS
    ald
    0.16
    .ai
    0.16
     Schultz
    0.14
    ¢åįķ
    0.14
    @class
    0.14
     Psi
    0.13
    497
    0.13
     cái
    0.13
    APPER
    0.13
    mia
    0.13
    Act Density 0.064%

    No Known Activations