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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal choice or decision-making in various scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erus
    -0.15
    iveau
    -0.14
    uga
    -0.14
    ilerden
    -0.14
    atif
    -0.14
    inet
    -0.14
    alus
    -0.13
    werp
    -0.13
    veyor
    -0.13
    ernes
    -0.13
    POSITIVE LOGITS
    606
    0.16
    озд
    0.15
    tent
    0.15
    hamster
    0.14
     cél
    0.14
    AAC
    0.13
    enso
    0.13
    Compatibility
    0.13
     strate
    0.13
    775
    0.13
    Act Density 0.033%

    No Known Activations