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

    Neuronpedia

    INDEX
    Explanations

    references to various types of problems or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     définiti
    -0.73
     navideños
    -0.73
     témo
    -0.71
     vectorielles
    -0.69
     mené
    -0.67
     espirituales
    -0.67
     clô
    -0.65
     virtuales
    -0.65
     memanfaatkan
    -0.64
    alignSelf
    -0.64
    POSITIVE LOGITS
     problems
    4.02
     Problems
    3.57
    problems
    3.51
     problem
    3.48
    Problems
    3.40
     PROBLEMS
    3.11
    problem
    3.09
     Problem
    3.00
    Problem
    2.90
     PROBLEM
    2.80
    Act Density 0.149%

    No Known Activations