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

    Neuronpedia

    INDEX
    Explanations

    occurrences of phrases that express conditional or restrictive statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¡¿
    -0.16
    lush
    -0.15
     Heck
    -0.14
    rink
    -0.14
    lun
    -0.14
    ToUpdate
    -0.14
    ãĥ¼ãĥ©
    -0.14
    hlen
    -0.14
    enne
    -0.14
    orton
    -0.14
    POSITIVE LOGITS
    anted
    0.15
    icha
    0.14
    dfa
    0.14
    drs
    0.14
     Coat
    0.14
    اÙģÙĩ
    0.14
     coat
    0.13
    Ïģιά
    0.13
    Dod
    0.13
    _NT
    0.13
    Act Density 0.000%

    No Known Activations