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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations or events in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gillian
    -0.45
    Qualitative
    -0.45
    XC
    -0.45
    Cecilia
    -0.45
    Kamu
    -0.44
    石川
    -0.43
    Basil
    -0.43
     Keluarga
    -0.43
     timp
    -0.42
     Utilizamos
    -0.42
    POSITIVE LOGITS
    đ
    0.69
    Đ
    0.69
     Đ
    0.68
     đ
    0.65
     Dorchester
    0.65
    AnchorStyles
    0.60
     Dons
    0.56
     Dougherty
    0.56
    kmäler
    0.54
    db
    0.52
    Act Density 0.005%

    No Known Activations