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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships and legacies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pagal
    -0.46
     незавершена
    -0.45
     genoux
    -0.39
    採
    -0.39
    Entry
    -0.38
    oga
    -0.38
    sha
    -0.37
    ך
    -0.37
     vlak
    -0.37
     fino
    -0.37
    POSITIVE LOGITS
     survivors
    1.06
    survi
    1.05
     Survivors
    0.98
     Survi
    0.97
     survived
    0.96
     left
    0.95
     survives
    0.95
    Survivors
    0.94
     Left
    0.92
     survive
    0.91
    Act Density 0.058%

    No Known Activations