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

    Neuronpedia

    INDEX
    Explanations

    references to potential situations or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Same
    -0.50
    aujourd
    -0.48
     kema
    -0.48
     aujourd
    -0.47
     élevées
    -0.47
     dayan
    -0.46
     cobr
    -0.46
     Same
    -0.45
     today
    -0.45
     része
    -0.44
    POSITIVE LOGITS
     potential
    1.67
    Potential
    1.54
    potential
    1.54
     Potential
    1.53
     potentially
    1.37
    Possible
    1.36
     POTENTIAL
    1.35
     possible
    1.33
    potentially
    1.29
     potencial
    1.28
    Act Density 0.253%

    No Known Activations