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

    Neuronpedia

    INDEX
    Explanations

    numerical data and comparisons in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    аниÑĨ
    -0.16
    enburg
    -0.16
    ovsky
    -0.15
    affen
    -0.14
    æ¾
    -0.14
    ¢åįķ
    -0.14
     Nich
    -0.14
    иÑģÑĤ
    -0.14
     CES
    -0.14
    uchi
    -0.13
    POSITIVE LOGITS
     hints
    0.22
     notes
    0.20
     minerals
    0.18
     leather
    0.17
    isphere
    0.17
     spice
    0.17
    notes
    0.17
     van
    0.16
     miner
    0.16
    bak
    0.16
    Act Density 0.016%

    No Known Activations