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

    Neuronpedia

    INDEX
    Explanations

    references to perception and assumptions about situations or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chiesto
    -0.53
     Act
    -0.53
     respectivement
    -0.51
     I
    -0.50
    бва
    -0.49
     yaptığı
    -0.49
     szól
    -0.48
     kece
    -0.47
    sprüng
    -0.47
     Kohn
    -0.47
    POSITIVE LOGITS
     seem
    1.02
     seems
    0.97
    Seems
    0.96
     CreateTagHelper
    0.95
    seems
    0.94
     scheint
    0.94
     seemed
    0.94
     Parece
    0.90
    enumi
    0.89
    seemed
    0.86
    Act Density 0.235%

    No Known Activations