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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to mechanical and powered systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.56
     Loyal
    -0.55
    majánló
    -0.52
    úrate
    -0.50
    ReusableCell
    -0.48
     localisation
    -0.48
     specialise
    -0.47
    expose
    -0.47
    ronomy
    -0.47
    hésite
    -0.47
    POSITIVE LOGITS
     strength
    0.46
     lift
    0.41
     lực
    0.40
     energy
    0.40
     Strength
    0.40
     power
    0.39
     force
    0.39
    OrNil
    0.39
    Strength
    0.39
     struggling
    0.38
    Act Density 0.412%

    No Known Activations