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

    Neuronpedia

    INDEX
    Explanations

    phrases related to removal or replacement processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     createState
    -0.59
    \{\\
    -0.54
    yaxis
    -0.52
    läge
    -0.51
    خطيط
    -0.51
    ernalia
    -0.50
     accompli
    -0.49
     Situs
    -0.48
    metry
    -0.47
    wertes
    -0.46
    POSITIVE LOGITS
    它们
    0.79
     these
    0.69
    它們
    0.69
    these
    0.67
    afficheront
    0.65
    them
    0.65
    HideFlags
    0.61
    These
    0.60
     Them
    0.59
    twimg
    0.59
    Act Density 0.334%

    No Known Activations