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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly those related to measurements or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.86
    wahlen
    -0.66
     of
    -0.63
     Imran
    -0.57
    Datuak
    -0.57
     propOrder
    -0.56
     JAXB
    -0.55
     dụ
    -0.54
     Graff
    -0.54
     ModelExpression
    -0.53
    POSITIVE LOGITS
     للمعارف
    0.80
     téléphonique
    0.72
     hvilken
    0.70
     icke
    0.68
     Shakspeare
    0.67
    zeiti
    0.67
     purpoſe
    0.67
     ſmall
    0.67
    etheless
    0.67
     Vira
    0.66
    Act Density 0.240%

    No Known Activations