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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intentions or aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aterno
    -0.16
    udden
    -0.16
    ñas
    -0.16
     itself
    -0.14
    ado
    -0.14
     promise
    -0.14
     Plan
    -0.14
    ayne
    -0.13
    .instant
    -0.13
    emez
    -0.13
    POSITIVE LOGITS
     eventual
    0.28
     eventually
    0.26
     soon
    0.25
    soon
    0.25
     Eventually
    0.21
     Soon
    0.20
    Soon
    0.20
    Eventually
    0.19
    æľīä¸Ģ
    0.18
     use
    0.18
    Act Density 0.072%

    No Known Activations