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

    Neuronpedia

    INDEX
    Explanations

    programming syntax, particularly related to lists and array indexing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.91
     EconPapers
    -0.76
    ubscribe
    -0.74
     osmosis
    -0.66
     Infórmanos
    -0.66
    __/
    -0.65
     boba
    -0.64
    brainly
    -0.62
    __))
    -0.62
     tarvit
    -0.62
    POSITIVE LOGITS
    [:,
    1.57
    [:
    1.31
    (:,
    1.18
    [:,:,
    1.00
    [...,
    0.78
    ๆ
    0.76
     autorytatywna
    0.74
    ][:
    0.74
     ax
    0.70
    ax
    0.70
    Act Density 0.047%

    No Known Activations