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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a new document or data entry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.51
     nearly
    -0.46
    casi
    -0.46
    Race
    -0.45
     Race
    -0.45
     réessayer
    -0.45
    пари
    -0.44
    DueDate
    -0.44
    gu
    -0.44
    match
    -0.43
    POSITIVE LOGITS
     threshold
    0.98
     hinaus
    0.86
     thresholds
    0.84
    threshold
    0.83
    IntoConstraints
    0.82
     themſelves
    0.76
     Threshold
    0.75
     seuil
    0.75
    THRESHOLD
    0.74
     leaſt
    0.72
    Act Density 0.471%

    No Known Activations