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

    Neuronpedia

    INDEX
    Explanations

    specific character sequences or substrings that likely represent names, titles, or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mán
    -0.16
    lamp
    -0.15
    اÙĦÙĩ
    -0.14
     znam
    -0.14
    zeich
    -0.13
    _TYPED
    -0.13
    BILE
    -0.13
    елеÑĦ
    -0.13
     Lage
    -0.13
    lice
    -0.13
    POSITIVE LOGITS
    ehr
    0.15
     Nim
    0.15
    igkeit
    0.14
    ffen
    0.14
     Nap
    0.14
    ovation
    0.14
     her
    0.14
    ler
    0.14
     income
    0.14
    enate
    0.14
    Act Density 0.032%

    No Known Activations