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

    Neuronpedia

    INDEX
    Explanations

    phrases related to economic growth and professional training

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amp
    -0.17
    ught
    -0.15
     herself
    -0.15
    unting
    -0.15
    odd
    -0.15
    ala
    -0.15
     flip
    -0.14
    ions
    -0.14
    uis
    -0.14
     itself
    -0.14
    POSITIVE LOGITS
    bes
    0.23
     apart
    0.22
    wich
    0.21
    Apart
    0.21
     considering
    0.20
     Apart
    0.20
     being
    0.20
     therefore
    0.19
     Therefore
    0.19
     besides
    0.19
    Act Density 0.202%

    No Known Activations