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

    Neuronpedia

    INDEX
    Explanations

    instances and concepts related to openness and accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wear
    -0.39
    ftagPool
    -0.38
    MessageTagHelper
    -0.38
     MainAxisSize
    -0.34
     tugas
    -0.34
    Iden
    -0.34
    EXACT
    -0.33
     epic
    -0.33
    wear
    -0.33
     vermeld
    -0.32
    POSITIVE LOGITS
     openness
    1.01
     ouverte
    0.98
     open
    0.97
     opened
    0.93
     opens
    0.90
     Opened
    0.90
     otev
    0.90
     terbuka
    0.88
     opening
    0.85
     ouvert
    0.85
    Act Density 0.375%

    No Known Activations