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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conducting tasks or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flattered
    -0.71
     BorderRadius
    -0.70
     ingrat
    -0.66
    Unmount
    -0.66
     retorted
    -0.64
    nutie
    -0.64
     importers
    -0.63
     SqlDbType
    -0.62
    पया
    -0.62
     stdin
    -0.62
    POSITIVE LOGITS
     performed
    1.52
    performed
    1.48
     perform
    1.44
     Perform
    1.33
     performing
    1.31
     PERFORM
    1.29
     performs
    1.29
     conducted
    1.28
    Perform
    1.27
     Performed
    1.26
    Act Density 0.263%

    No Known Activations