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

    Neuronpedia

    INDEX
    Explanations

    references to the process of correcting or updating information

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    <!--[
    -0.65
    ParallelGroup
    -0.64
    tvguidetime
    -0.57
     Vio
    -0.55
     parap
    -0.53
     _$
    -0.53
     Nark
    -0.53
     contribution
    -0.52
    ↵
    -0.52
     Kombat
    -0.52
    POSITIVE LOGITS
     corrected
    2.19
     Corrected
    1.61
    corrected
    1.42
    Corrected
    1.25
     corrects
    1.10
     correcting
    1.05
     corrig
    0.88
     correg
    0.75
     corregir
    0.74
     rectified
    0.67
    Act Density 0.002%

    No Known Activations