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

    Neuronpedia

    INDEX
    Explanations

    assertions and conclusions supported by research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARRANT
    -0.16
    ammen
    -0.15
    ester
    -0.15
    ër
    -0.14
    undry
    -0.14
    à¹Ĥย
    -0.14
    Orth
    -0.14
    ữa
    -0.14
    gue
    -0.14
    _ROUND
    -0.14
    POSITIVE LOGITS
    941
    0.15
    537
    0.15
    605
    0.15
    eon
    0.15
    ÙĪا
    0.14
     sight
    0.14
    atom
    0.14
     bench
    0.14
    fe
    0.14
    959
    0.14
    Act Density 0.141%

    No Known Activations