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

    Neuronpedia

    INDEX
    Explanations

    terms related to finality and classification of entities or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ations
    -0.20
    ating
    -0.17
    ants
    -0.17
    undry
    -0.17
    arest
    -0.17
    ativity
    -0.17
    elian
    -0.16
    arity
    -0.16
    ature
    -0.16
    atures
    -0.16
    POSITIVE LOGITS
    mente
    0.44
    izado
    0.41
    izada
    0.41
    izados
    0.39
    izar
    0.36
    izando
    0.35
    iz
    0.35
    ización
    0.34
    iza
    0.34
    ment
    0.34
    Act Density 0.028%

    No Known Activations