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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with movement or position changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Huerta
    -0.55
    WriteLiteral
    -0.53
    unauthorized
    -0.52
    DeleteMapping
    -0.52
     الرياضيه
    -0.51
    飽
    -0.50
     geslacht
    -0.49
    SerializeField
    -0.48
     Marquette
    -0.48
    стно
    -0.48
    POSITIVE LOGITS
     retreat
    1.04
     retreated
    1.00
     retreating
    1.00
     backward
    0.99
     backwards
    0.98
     recul
    0.94
     retreats
    0.93
     Retreat
    0.92
     regress
    0.91
     Backing
    0.89
    Act Density 0.277%

    No Known Activations