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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to compensation and equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.64
    – 
    -0.52
    Bran
    -0.51
     ſei
    -0.51
     ſur
    -0.51
     Fun
    -0.49
    $_['
    -0.49
     circ
    -0.48
    kháu
    -0.47
    олові
    -0.47
    POSITIVE LOGITS
     probability
    0.61
     MainAxisSize
    0.61
     payment
    0.59
     recompensa
    0.57
     compensation
    0.53
     fotográfico
    0.52
    Sklici
    0.52
     récompenses
    0.50
     collaborateurs
    0.50
     cooperación
    0.50
    Act Density 0.282%

    No Known Activations