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

    Neuronpedia

    INDEX
    Explanations

    references to factors in a scientific or mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McGuire
    -0.55
    psum
    -0.54
     pilgrimage
    -0.53
     CNG
    -0.52
     pulito
    -0.52
    ennett
    -0.52
    corrhi
    -0.51
    hubanes
    -0.51
     commerciaux
    -0.50
    lawayo
    -0.50
    POSITIVE LOGITS
     factor
    4.88
     Factor
    4.41
    factor
    4.33
    Factor
    4.09
     FACTOR
    3.96
     factors
    3.88
     Factors
    3.56
    factors
    3.55
    FACTOR
    3.32
     FACTORS
    3.27
    Act Density 0.115%

    No Known Activations