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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases related to relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansa
    -0.16
     Christ
    -0.15
    вай
    -0.14
     Fri
    -0.14
    MAL
    -0.14
     Mal
    -0.14
     way
    -0.14
     charge
    -0.14
    esus
    -0.14
    زاÙĨ
    -0.14
    POSITIVE LOGITS
    idency
    0.16
    abei
    0.15
    нод
    0.15
    ailability
    0.15
    claimer
    0.15
    entials
    0.15
    oucher
    0.15
    alon
    0.15
     seper
    0.15
    cour
    0.15
    Act Density 0.000%

    No Known Activations