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

    Neuronpedia

    INDEX
    Explanations

    phrases related to executing tasks or completing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    embr
    -0.17
    obil
    -0.16
    rou
    -0.15
     cass
    -0.15
    CTS
    -0.15
    atz
    -0.14
    kart
    -0.14
    ibraltar
    -0.14
    upro
    -0.14
    kat
    -0.13
    POSITIVE LOGITS
    ship
    0.15
    ynes
    0.15
    ä¼´
    0.15
    наÑĩе
    0.14
    ion
    0.14
    ono
    0.14
    observer
    0.13
     sami
    0.13
    grown
    0.13
    postalcode
    0.13
    Act Density 0.008%

    No Known Activations