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

    Neuronpedia

    INDEX
    Explanations

    instances of variable declarations and assignments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.92
     Theſe
    -0.68
     tork
    -0.68
     conden
    -0.66
     sover
    -0.66
     Schwä
    -0.65
     sach
    -0.65
     Venkates
    -0.65
     disting
    -0.64
    ...";
    -0.64
    POSITIVE LOGITS
     i
    1.18
    I
    1.13
     I
    1.09
     iArr
    1.05
     iVar
    0.99
     jLabel
    0.90
    iI
    0.89
    튿
    0.89
     oiseaux
    0.86
    आई
    0.86
    Act Density 0.183%

    No Known Activations