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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating states, actions, and conditions, especially in relation to obligations or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    also
    -0.22
     also
    -0.19
    already
    -0.19
     already
    -0.19
     previously
    -0.18
     Already
    -0.18
     often
    -0.18
     Also
    -0.18
     também
    -0.17
    often
    -0.17
    POSITIVE LOGITS
    iked
    0.16
    luv
    0.14
    OKIE
    0.14
     WARRANT
    0.14
     Innoc
    0.14
    ppo
    0.14
    .FileSystem
    0.13
    unos
    0.13
    ENARIO
    0.13
    CALE
    0.13
    Act Density 0.081%

    No Known Activations