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

    Neuronpedia

    INDEX
    Explanations

    references to methods, conditions, and categorical data in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engesch
    -0.40
    enej
    -0.38
     étoit
    -0.37
    cemment
    -0.37
     borracha
    -0.36
     potrivit
    -0.35
     debout
    -0.35
     înal
    -0.34
     vecind
    -0.34
     viņ
    -0.34
    POSITIVE LOGITS
     are
    1.40
     serem
    0.97
    are
    0.88
     eivät
    0.87
     έχουν
    0.86
     were
    0.84
     đều
    0.84
     muszą
    0.83
     mają
    0.82
     estão
    0.81
    Act Density 0.903%

    No Known Activations