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

    Neuronpedia

    INDEX
    Explanations

    technical terms and jargon related to heavy machinery and energy systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.63
     Entered
    -0.56
    ````
    -0.54
     conscientious
    -0.53
     quir
    -0.51
     sanity
    -0.51
     cob
    -0.50
     churn
    -0.49
     Burton
    -0.48
     sneaky
    -0.48
    POSITIVE LOGITS
     respectively
    0.73
    ohm
    0.64
     alike
    0.64
    rican
    0.62
    ciation
    0.58
    rylic
    0.56
    orem
    0.56
    idae
    0.55
    ilon
    0.55
    ariat
    0.55
    Act Density 0.488%

    No Known Activations