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

    Neuronpedia

    INDEX
    Explanations

    phrases related to standing firm or taking a position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anglès
    -0.68
     initComponents
    -0.63
     Nark
    -0.61
     Gables
    -0.59
    numerusform
    -0.57
    Rè
    -0.56
    "?>
    -0.54
    cible
    -0.54
    ్వ
    -0.54
    soever
    -0.54
    POSITIVE LOGITS
     Stand
    1.05
    Stand
    0.98
     STAND
    0.96
     Stands
    0.96
     stood
    0.91
    STAND
    0.90
     stands
    0.90
     stand
    0.88
     debout
    0.81
     Standing
    0.77
    Act Density 0.144%

    No Known Activations